Detection of a concealed prohibited material in an item, using image processing

A method comprising, by one or more processing circuitries:

• obtaining an image of an item of a given category, acquired by an acquisition device,
• determining a first area of the image corresponding to a first element of the item, wherein the first element of the item belongs to a predefined first sub-category of elements present in items of the given category,
• determining a second area of the image corresponding to a second element of the item,
• wherein the second element is different from the first element, wherein the second element of the item belongs to a predefined second sub-category of elements present in items of the given category, wherein the predefined second sub-category differs from the predefined first sub-category,
• obtaining data Dfirst part informative of a pixel intensity of the first element of the predefined first sub-category in the image,
• obtaining data Dsecond part informative of a pixel intensity of the second element of the predefined second sub-category in the image,
• obtaining data Dpositive, first part informative of a pixel intensity in one or more first images of one or more first items of the given category that comprise one or more first elements of the predefined first sub-category of elements, wherein the one or more first elements of the predefined first sub-category are associated with a prohibited material, wherein the data Dpositive, first part comprises, for each given pixel intensity value of a plurality of different pixel intensity values in the one or more first images, a probability that this given pixel intensity value is informative of a prohibited material;
• obtaining data Dnegative, first part informative of a pixel intensity in one or more second images of one or more second items of the given category that comprise one or more second elements of the predefined second sub-category of elements, wherein the one or more second elements of the predefined second sub-category of elements are not associated with a prohibited material, wherein the data Dnegative, first part includes, for each given pixel intensity value of a plurality of different pixel intensity values in the one or more second images, a probability that this given pixel intensity value is not informative of a prohibited material;
• obtaining data Dpositive, second part informative of a pixel intensity in one or more third images of one or more third items of the given category that comprise one or more third elements of the predefined second sub-category of elements, wherein the one or more third elements of the predefined second sub-category are associated with a prohibited material, wherein the data Dpositive, second part comprises, for each given pixel intensity value of a plurality of different pixel intensity values in the one or more third images, a probability that this given pixel intensity value is informative of a prohibited material;
• obtaining data Dnegative, second part informative of a pixel intensity in one or more fourth images of one or more fourth items of the given category that comprise one or more fourth elements of the predefined second sub-category of elements, wherein the one or more fourth elements of the predefined second sub-category of elements are not associated with a prohibited material, wherein the data Dnegative, second part includes, for each given pixel intensity value of a plurality of different pixel intensity values in the one or more fourth images, a probability that this given pixel intensity value is not informative of a prohibited material;
• using the data Dpositive, first part, the data Dnegative, first part and the data Dfirst part to detect whether the first element of the item is associated with a concealed prohibited material in the image, and
• using the data Dpositive, second part, the data Dnegative, second part and the data Dsecond part to detect whether the second element of the item is associated with a concealed prohibited material in the image.

A non-transitory storage device readable by one or more processing circuitries, tangibly embodying a program of instructions executable by the one or more processing circuitries to perform:

• obtaining an image of an item of a given category, acquired by an acquisition device,
• determining a first area of the image corresponding to a first element of the item, wherein the first element of the item belongs to a predefined first sub-category of elements present in items of the given category,
• determining a second area of the image corresponding to a second element of the item,
• wherein the second element is different from the first element, wherein the second element of the item belongs to a predefined second sub-category of elements present in items of the given category, wherein the predefined second sub-category differs from the predefined first sub-category,
• obtaining data Dfirst part informative of a pixel intensity of the first element of the predefined first sub-category in the image,
• obtaining data Dsecond part informative of a pixel intensity of the second element of the predefined second sub-category in the image,
• obtaining data Dpositive, first part informative of a pixel intensity in one or more first images of one or more first items of the given category that comprise one or more first elements of the predefined first sub-category of elements, wherein the one or more first elements of the predefined first sub-category are associated with a prohibited material, wherein the data Dpositive, first part comprises, for each given pixel intensity value of a plurality of different pixel intensity values in the one or more first images, a probability that this given pixel intensity value is informative of a prohibited material;
• obtaining data Dnegative, first part informative of a pixel intensity in one or more second images of one or more second items of the given category that comprise one or more second elements of the predefined second sub-category of elements, wherein the one or more second elements of the predefined second sub-category of elements are not associated with a prohibited material, wherein the data Dnegative, first part includes, for each given pixel intensity value of a plurality of different pixel intensity values in the one or more second images, a probability that this given pixel intensity value is not informative of a prohibited material;
• obtaining data Dpositive, second part informative of a pixel intensity in one or more third images of one or more third items of the given category that comprise one or more third elements of the predefined second sub-category of elements, wherein the one or more third elements of the predefined second sub-category are associated with a prohibited material, wherein the data Dpositive, second part comprises, for each given pixel intensity value of a plurality of different pixel intensity values in the one or more third images, a probability that this given pixel intensity value is informative of a prohibited material;
• obtaining data Dnegative, second part informative of a pixel intensity in one or more fourth images of one or more fourth items of the given category that comprise one or more fourth elements of the predefined second sub-category of elements, wherein the one or more fourth elements of the predefined second sub-category of elements are not associated with a prohibited material, wherein the data Dnegative, second part includes, for each given pixel intensity value of a plurality of different pixel intensity values in the one or more fourth images, a probability that this given pixel intensity value is not informative of a prohibited material;
• using the data Dpositive, first part, the data Dnegative, first part and the data Dfirst part to detect whether the first element of the item is associated with a concealed prohibited material in the image, and
• using the data Dpositive, second part, the data Dnegative, second part and the data Dsecond part to detect whether the second element of the item is associated with a concealed prohibited material in the image.