# US 2025/0095134 A1 · Methods and systems for visual inspection of products

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0095134 A1
- Document ID: US20250095134A1
- Status: Published application
- Kind: A1
- Application number: 18/368,443
- Filed: 2023-09-14
- Published: 2025-03-20
- Earliest claimed: 2023-09-14
- Assignees: Panasonic Intellectual Property Management Co., Ltd.
- Applicants: Panasonic Intellectual Property Management Co., Ltd.
- Inventors: Andre IVAN; Zong Sheng TANG; Ariel BECK
- Web page: https://patentgrep.com/patent/US20250095134A1

## CPC

- G06T 7/0008: {checking presence/absence}
- G06T 7/0004: {Industrial image inspection}
- G06T 7/001: {using an image reference approach}
- G06T 7/12: Edge-based segmentation
- G06T 7/60: Analysis of geometric attributes
- G06V 10/25: Determination of region of interest [ROI] or a volume of interest [VOI]
- G06V 10/82: using neural networks
- G06V 30/1448: {based on markings or identifiers characterising the document or the area}
- G06V 30/15: {Cutting or merging image elements, e.g. region growing, watershed or clustering-based techniques}
- G06V 30/1801: {Detecting partial patterns, e.g. edges or contours, or configurations, e.g. loops, corners, strokes or intersections (extracting features by contour coding G06V30/182)}
- G06V 30/18086: {by performing operations within image blocks or by using histograms}
- G06V 30/19073: {Comparing statistics of pixel or of feature values, e.g. histogram matching}
- G06V 30/1916: {Validation; Performance evaluation}
- G06T 2200/24: involving graphical user interfaces [GUIs]
- G06T 2207/20076: Probabilistic image processing
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/20132: Image cropping
- G06T 2207/30108: Industrial image inspection
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

The present disclosure discloses a method and system for visual inspection of a target product. The method includes a) receiving an image associated with the target product; generating a plurality of region of interests (ROIs) associated with the image; identifying, based on the plurality of non-terminal ROIs, a first set of features and a second set of features associated with the image. The first set of features and the second set of features are indicative of one of a presence of defect within the image or an absence of defect within the image. The method also includes determining, based on the first set of features and the second set of features, a result of the visual inspection of the target product associated with the image. The result is a success result or a failure result.

## Claims

### Claim 1

A method for visual inspection of a target product, the method comprising:
receiving an image associated with the target product;
generating a plurality of region of interests (ROIs) associated with the image, wherein the plurality of ROIs comprises a plurality of terminal ROIs and a plurality of non-terminal ROIs;
identifying, based on the plurality of non-terminal ROIs, a first set of features and a second set of features associated with the image, wherein the first set of features and the second set of features are indicative of one of a presence of defect within the image or an absence of defect within the image; and
determining, based on the first set of features and the second set of features, a result of the visual inspection of the target product associated with the image, wherein the result is one of a success result or a failure result.

### Claim 2 (depends on 1)

The method of claim 1, wherein determining the result of the visual inspection of the target product associated with the image comprises:
providing the first set of features and the second set of features as an input to an artificial intelligence (AI) model;
receiving, from the AI model, a prediction value indicative of one of a probability of presence of defect within the image or a probability of absence of defect within the image;
comparing the prediction value with a predetermined threshold; and
determining the result of the visual inspection to be one of the success result or the failure result based on the comparison.

### Claim 3 (depends on 1)

The method of claim 1, wherein generating the plurality of ROIs comprises:
determining an orientation associated with the received image based on an edge filtering technique;
determining at least one image corner and at least one terminal corner associated with the received image based on the edge filtering technique;
generating a cropped image based on determined orientation, the determined at least one image corner and the determined at least one terminal corner; and
generating the plurality of ROIs based on the cropped image.

### Claim 4 (depends on 3)

The method of claim 3, wherein prior to identifying the first set of features and the second set of features, the method comprises:
determining, based on the at least one terminal corner, whether a terminal of the target product is associated with a defective length;
upon determining that the terminal of the target product is not associated with the defective length, identifying the first set of features and the second set of features associated with the image; and
upon determining that the terminal of the target product is associated with the defective length, determining the result of the visual inspection to be a failure result.

### Claim 5 (depends on 1)

The method of claim 1, wherein identifying the first set of features comprises:
extracting, from each non-terminal ROI of the plurality of non-terminal ROIs, one or more statistical features;
generating the first set of features based on the extracted one or more statistical features from each non-terminal ROI of the plurality of non-terminal ROIs.

### Claim 6 (depends on 1)

The method of claim 1, wherein identifying the second set of features comprises:
generating one or more bounding boxes within the image;
for each bounding box of the one or more bounding boxes:
identifying at least one pixel blob based on a plurality of pixels within the bounding box;
associating the at least one pixel blob with one of a character within the bounding box or a defect within the bounding box;
generating a processed image based on the association of the at least one pixel blob of each bounding box of the one or more bounding boxes; and
extracting the second set of features from the processed image based on a Histogram of Gradient (HOG) extracting technique.

### Claim 7 (depends on 6)

The method of claim 6, wherein generating the one or more bounding boxes comprise:
determining a first ROI from among the plurality of ROIs within the image, the first ROI being indicative of an area of the image comprising one or more characters;
detecting the one or more characters within the first ROI based on a character detection technique; and
for each detected character of the one or more characters, generating a bounding box associated with the corresponding character, thereby generating the one or more bounding boxes.

### Claim 8 (depends on 6)

The method of claim 6, wherein identifying the at least one pixel blob comprises:
for each bounding box:
determining a pixel value associated with each pixel of the plurality of pixels within the bounding box;
comparing, with a pixel value threshold, the pixel value associated with each pixel;
identifying at least one first set of pixels from among the plurality of pixels based on the comparison, wherein the pixel value of each pixel of the at least one first set of pixels is greater than the pixel value threshold; and
determining the at least one first set of pixels as the at least one pixel blob within the bounding box.

### Claim 9 (depends on 8)

The method of claim 8, wherein associating the at least one pixel blob with one of the character or the defect comprises:
for each bounding box:
determining a size of the at least one blob based on a number of the at least one first set of pixels associated with the at least one blob;
determining whether the size of the at least one blob is within a first threshold range;
upon determining that the size of the at least one blob is within the first threshold range, associating the at least blob with the character within the bounding box; and
upon determining that the size of the blob is not within the first threshold range, associating the at least one blob with the defect within the bounding box.

### Claim 10 (depends on 6)

The method of claim 6, wherein generating the processed image comprises:
for each bounding box, when the at least one blob is associated with the character within the bounding box:
removing, from the image, the character to form a respective space within the image;
determining a mean pixel value associated with the image; and
filling the respective space within the image with one or more new pixels having the mean pixel value.

### Claim 11 (depends on 10)

The method of claim 10, further comprising:
for each bounding box:
when the at least one blob is associated with the defect within the bounding box, retaining the defect within the image.

### Claim 12 (depends on 9)

The method of claim 9, further comprising, prior to extracting the second set of features:
identifying, within the processed image, one or more additional pixel blobs based on one or more second set of pixels within the processed image; wherein each pixel of the one or more second set of pixels has a corresponding pixel value greater than the pixel value threshold;
determining a corresponding size of the one or more additional pixel blobs within the processed image;
determining whether the corresponding size of the one or more additional pixel blobs is within a second threshold range;
upon determining that the corresponding size of the one or more additional pixel blobs is within the second threshold range, associating the one or more additional pixel blobs with a corresponding remaining character within the processed image; and
upon determining that the corresponding size of the one or more additional pixel blobs is not within the second threshold range, associating the one or more additional pixel blobs with a corresponding remaining defect within the processed image.

### Claim 13 (depends on 12)

The method of claim 12, further comprising:
when the one or more additional pixel blobs are associated with the corresponding remaining character within the processed image:
removing, from the processed image, the corresponding remaining character to form a respective space within the processed image; and
filling the respective space within the processed image with the mean pixel value; and
when the one or more additional pixel blobs are associated with a corresponding remaining defect, retaining the corresponding defect within the processed image.

### Claim 14 (depends on 12)

The method of claim 12, wherein:
the first threshold range comprises a first lower threshold and a first upper threshold,
the second threshold range comprises a second lower threshold and a second upper threshold,
the first upper threshold is greater than the second upper threshold, and
the first lower threshold is lower than the second lower threshold.

### Claim 15 (depends on 1)

The method of claim 1, further comprising one or more of:
storing the result of the visual inspection of the target product in a database; and
displaying the result of the visual inspection of the target product on a user interface.

### Claim 16

A method for extracting features from an image associated with a target product, the method comprising:
receiving the image associated with the target product;
identifying at least one pixel blob within the image;
associating the at least one pixel blob with one of a character or a defect;
generating a processed image based on said association, wherein generating the processed image comprises:
when the at least one blob is associated with the character:
removing, from the image, the character to form a respective space within the image;
determining a mean pixel value associated with the image; and
filling the respective space within the image with one or more new pixels having the mean pixel value;
when the at least one blob is associated with the defect, retaining the defect within the image; and
extracting one or more features from the processed image based on a Histogram of Gradient (HOG) extracting technique.

### Claim 17 (depends on 16)

The method of claim 16, comprising:
determining a ROI within the image, the ROI being indicative of an area of the image comprising one or more characters;
detecting the one or more characters within the ROI based on a character detection technique;
generating one or more bounding boxes by generating a bounding box associated with a corresponding character of the one or more characters,
wherein identifying at least one pixel blob within the image comprises identifying, for each bounding box, the at least one pixel blob, and
wherein associating the at least one pixel blob with one of a character or a defect comprises associating, for each bounding box, the at least one pixel blob with one of the character or the defect within the bounding box.

### Claim 18 (depends on 17)

The method of claim 17, wherein identifying the at least one pixel blob comprises:
for each bounding box:
determining a pixel value associated with each pixel of the plurality of pixels within the bounding box;
comparing, with a pixel value threshold, the pixel value associated with each pixel;
identifying at least one first set of pixels from among the plurality of pixels based on the comparison, wherein the pixel value of each pixel of the at least one first set of pixels is greater than the pixel value threshold; and
determining the at least one first set of pixels as the at least one pixel blob within the bounding box.

### Claim 19 (depends on 18)

The method of claim 18, wherein associating the at least one pixel blob with one of the character or the defect comprises:
for each bounding box:
determining a size of the at least one blob based on a number of the at least one first set of pixels associated with the at least one blob;
determining whether the size of the at least one blob is within a first threshold range;
upon determining that the size of the at least one blob is within the first threshold range, associating the at least blob with the character within the bounding box; and
upon determining that the size of the blob is not within the first threshold range, associating the at least one blob with the defect within the bounding box.

### Claim 20 (depends on 16)

The method of claim 16, further comprising, prior to extracting the one or more features:
identifying, within the processed image, one or more additional pixel blobs based on one or more second set of pixels within the processed image; wherein each pixel of the one or more second set of pixels has a corresponding pixel value greater than the pixel value threshold;
determining a corresponding size of the one or more additional pixel blobs within the processed image;
determining whether the corresponding size of the one or more additional pixel blobs is within a second threshold range;
upon determining that the corresponding size of the one or more additional pixel blobs is within the second threshold range, associating the one or more additional pixel blobs with a corresponding remaining character within the processed image;
upon determining that the corresponding size of the one or more additional pixel blobs is not within the second threshold range, associating the one or more additional pixel blobs with a corresponding remaining defect within the processed image;
when the one or more additional pixel blobs are associated with the corresponding remaining character within the processed image:
removing, from the processed image, the corresponding remaining character to form a respective space within the processed image; and
filling the respective space within the processed image with the mean pixel value; and
when the one or more additional pixel blobs are associated with a corresponding remaining defect, retaining the corresponding defect within the processed image.

### Claim 21 (depends on 20)

The method of claim 20, wherein:
the first threshold range comprises a first lower threshold and a first upper threshold,
the second threshold range comprises a second lower threshold and a second upper threshold,
the first upper threshold is greater than the second upper threshold, and
the first lower threshold is lower than the second lower threshold.

### Claim 22

A system for visual inspection of a target product, the system comprising:
a memory; and
at least one processor communicably coupled with the memory, the at least one processor being configured to:
receive an image associated with the target product;
generate a plurality of region of interests (ROIs) associated with the image, wherein the plurality of ROIs comprises a plurality of terminal ROIs and a plurality of non-terminal ROIs;
identify, based on the plurality of non-terminal ROIs, a first set of features and a second set of features associated with the image, wherein the first set of features and the second set of features are indicative of one of a presence of defect within the image or an absence of defect within the image; and
determine, based on the first set of features and the second set of features, a result of the visual inspection of the target product associated with the image, wherein the result is one of a success result or a failure result.

### Claim 23 (depends on 22)

The system of claim 22, wherein to determine the result of the visual inspection of the target product associated with the image, the at least one processor is configured to:
provide the first set of features and the second set of features as an input to an artificial intelligence (AI) model;
receive, from the AI model, a prediction value indicative of one of a probability of presence of defect within the image or a probability of absence of defect within the image;
compare the prediction value with a predetermined threshold; and
determine the result of the visual inspection to be one of the success result or the failure result based on the comparison.

### Claim 24 (depends on 22)

The system of claim 22, wherein to generate the plurality of ROIs, the at least one processor is configured to:
determine an orientation associated with the received image based on an edge filtering technique;
determine at least one image corner and at least one terminal corner associated with the received image based on the edge filtering technique;
generate a cropped image based on determined orientation, the determined at least one image corner and the determined at least one terminal corner; and
generate the plurality of ROIs based on the cropped image.

### Claim 25 (depends on 24)

The system of claim 24, wherein prior to identifying the first set of features and the second set of features, the at least one processor is configured to:
determine, based on the at least one terminal corner, whether a terminal of the target product is associated with a defective length;
upon a determination that the terminal of the target product is not associated with the defective length, identify the first set of features and the second set of features associated with the image; and
upon a determination that the terminal of the target product is associated with the defective length, determine the result of the visual inspection to be a failure result.

### Claim 26 (depends on 22)

The system of claim 22, wherein to identify the first set of features, the at least one processor is configured to:
extract, from each non-terminal ROI of the plurality of non-terminal ROIs, one or more statistical features;
generate the first set of features based on the extracted one or more statistical features from each non-terminal ROI of the plurality of non-terminal ROIs.

### Claim 27 (depends on 22)

The system of claim 22, wherein to identify the second set of feature, the at least one processor is configured to:
generate one or more bounding boxes within the image;
for each bounding box of the one or more bounding boxes:
identify at least one pixel blob based on a plurality of pixels within the bounding box;
associate the at least one pixel blob with one of a character within the bounding box or a defect within the bounding box;
generate a processed image based on the association of the at least one pixel blob of each bounding box of the one or more bounding boxes; and
extract the second set of features from the processed image based on a Histogram of Gradient (HOG) extracting technique.

### Claim 28 (depends on 27)

The system of claim 27, wherein to generate the one or more bounding boxes, the at least one processor is configured to:
determine a first ROI from among the plurality of ROIs within the image, the first ROI being indicative of an area of the image comprising one or more characters;
detect the one or more characters within the first ROI based on a character detection technique; and
for each detected character of the one or more characters, generate a bounding box associated with the corresponding character, thereby generating the one or more bounding boxes.

### Claim 29 (depends on 27)

The system of claim 27, wherein to identify the at least one pixel blob, the at least one processor is configured to:
for each bounding box:
determine a pixel value associated with each pixel of the plurality of pixels within the bounding box;
compare, with a pixel value threshold, the pixel value associated with each pixel;
identify at least one first set of pixels from among the plurality of pixels based on the comparison, wherein the pixel value of each pixel of the at least one first set of pixels is greater than the pixel value threshold; and
determine the at least one first set of pixels as the at least one pixel blob within the bounding box.

### Claim 30 (depends on 29)

The system of claim 29, wherein to associate the at least one pixel blob with one of the character or the defect, the at least one processor is configured to:
for each bounding box:
determine a size of the at least one blob based on a number of the at least one first set of pixels associated with the at least one blob;
determine whether the size of the at least one blob is within a first threshold range;
upon a determination that the size of the at least one blob is within the first threshold range, associate the at least blob with the character within the bounding box; and
upon a determination that the size of the blob is not within the first threshold range, associate the at least one blob with the defect within the bounding box.

### Claim 31 (depends on 27)

The system of claim 27, wherein to generate the processed image, the at least one processor is configured to:
for each bounding box, when the at least one blob is associated with the character within the bounding box:
remove, from the image, the character to form a respective space within the image;
determine a mean pixel value associated with the image; and
fill the respective space within the image with one or more new pixels having the mean pixel value.

### Claim 32 (depends on 31)

The system of claim 31, wherein the at least one processor is further configured to:
for each bounding box:
when the at least one blob is associated with the defect within the bounding box, retain the defect within the image.

### Claim 33 (depends on 30)

The system of claim 30, wherein the at least one processor is further configured to, prior to extracting the second set of features:
identify, within the processed image, one or more additional pixel blobs based on one or more second set of pixels within the processed image; wherein each pixel of the one or more second set of pixels has a corresponding pixel value greater than the pixel value threshold;
determine a corresponding size of the one or more additional pixel blobs within the processed image;
determine whether the corresponding size of the one or more additional pixel blobs is within a second threshold range;
upon a determination that the corresponding size of the one or more additional pixel blobs is within the second threshold range, associate the one or more additional pixel blobs with a corresponding remaining character within the processed image; and
upon a determination that the corresponding size of the one or more additional pixel blobs is not within the second threshold range, associate the one or more additional pixel blobs with a corresponding remaining defect within the processed image.

### Claim 34 (depends on 33)

The system of claim 33, wherein the at least one processor is further configured to:
when the one or more additional pixel blobs are associated with the corresponding remaining character within the processed image:
remove, from the processed image, the corresponding remaining character to form a respective space within the processed image; and
fill the respective space within the processed image with the mean pixel value; and
when the one or more additional pixel blobs are associated with a corresponding remaining defect, retain the corresponding defect within the processed image.

### Claim 35 (depends on 33)

The system of claim 33, wherein:
the first threshold range comprises a first lower threshold and a first upper threshold,
the second threshold range comprises a second lower threshold and a second upper threshold,
the first upper threshold is greater than the second upper threshold, and
the first lower threshold is lower than the second lower threshold.

### Claim 36 (depends on 22)

The system as claimed in claim 22, wherein the at least one processor is configured to perform one or more of:
store the result of the visual inspection of the target product in a database; and
display the result of the visual inspection of the target product on a user interface.

### Claim 37

A system to extract features from an image associated with a target product, the system comprising:
a memory; and
at least one processor communicably coupled with the memory, the at least one processor being configured to:
receive the image associated with the target product;
identify at least one pixel blob within the image;
associate the at least one pixel blob with one of a character or a defect;
generate a processed image based on said association, wherein to generate the processed image, the at least one processor is configured to:
when the at least one blob is associated with the character:
remove, from the image, the character to form a respective space within the image;
determine a mean pixel value associated with the image; and
fill the respective space within the image with one or more new pixels having the mean pixel value;
when the at least one blob is associated with the defect, retain the defect within the image; and
extract one or more features from the processed image based on a Histogram of Gradient (HOG) extracting technique.

### Claim 38 (depends on 37)

The system of claim 37, wherein the at least one processor is further configured to:
determine a ROI within the image, the ROI being indicative of an area of the image comprising one or more characters;
detect the one or more characters within the ROI based on a character detection technique;
generate one or more bounding boxes by generating a bounding box associated with a corresponding character of the one or more characters,
wherein to identify at least one pixel blob within the image, the at least one processor is configured to identify, for each bounding box, the at least one pixel blob, and
wherein to associate the at least one pixel blob with one of a character or a defect, the at least one processor is configured to associate, for each bounding box, the at least one pixel blob with one of the character or the defect within the bounding box.

### Claim 39 (depends on 38)

The system of claim 38, wherein to identify the at least one pixel blob, the at least one processor is configured to:
for each bounding box:
determine a pixel value associated with each pixel of the plurality of pixels within the bounding box;
compare, with a pixel value threshold, the pixel value associated with each pixel;
identify at least one first set of pixels from among the plurality of pixels based on the comparison, wherein the pixel value of each pixel of the at least one first set of pixels is greater than the pixel value threshold; and
determine the at least one first set of pixels as the at least one pixel blob within the bounding box.

### Claim 40 (depends on 39)

The system of claim 39, wherein to associate the at least one pixel blob with one of the character or the defect, the at least one processor is configured to:
for each bounding box:
determine a size of the at least one blob based on a number of the at least one first set of pixels associated with the at least one blob;
determine whether the size of the at least one blob is within a first threshold range;
upon a determination that the size of the at least one blob is within the first threshold range, associate the at least blob with the character within the bounding box; and
upon a determination that the size of the blob is not within the first threshold range, associate the at least one blob with the defect within the bounding box.

### Claim 41 (depends on 37)

The system of claim 37, wherein, prior to extracting the one or more features, the at least one processor is further configured to:
identify, within the processed image, one or more additional pixel blobs based on one or more second set of pixels within the processed image; wherein each pixel of the one or more second set of pixels has a corresponding pixel value greater than the pixel value threshold;
determine a corresponding size of the one or more additional pixel blobs within the processed image;
determine whether the corresponding size of the one or more additional pixel blobs is within a second threshold range;
upon a determination that the corresponding size of the one or more additional pixel blobs is within the second threshold range, associate the one or more additional pixel blobs with a corresponding remaining character within the processed image;
upon a determination that the corresponding size of the one or more additional pixel blobs is not within the second threshold range, associate the one or more additional pixel blobs with a corresponding remaining defect within the processed image;
when the one or more additional pixel blobs are associated with the corresponding remaining character within the processed image:
remove, from the processed image, the corresponding remaining character to form a respective space within the processed image; and
fill the respective space within the processed image with the mean pixel value; and
when the one or more additional pixel blobs are associated with a corresponding remaining defect, retain the corresponding defect within the processed image.

### Claim 42 (depends on 41)

The system of claim 41, wherein:
the first threshold range comprises a first lower threshold and a first upper threshold,
the second threshold range comprises a second lower threshold and a second upper threshold,
the first upper threshold is greater than the second upper threshold, and
the first lower threshold is lower than the second lower threshold.