Object recognition apparatus and operation method thereof

An operation method of an object recognition apparatus, the operation method comprising:

• obtaining, by using one or more spectrometers, at least one from a first type of spectrum data and a second type of spectrum data from light scattered, emitted, or reflected from an object;
• obtaining image data of the object by using an image sensor;
• and
• identifying the object using at least two from among the first type of spectrum data, the second type of spectrum data, and the image data and using at least two pattern recognition algorithms,
• wherein the at least two pattern recognition algorithms comprise a first pattern recognition algorithm that uses data obtained from one from among a first spectrometer included in the one or more spectrometers, a second spectrometer included in the one or more spectrometers, and the image sensor as input data and a second pattern recognition algorithm that uses data obtained from a different one from among the first spectrometer, the second spectrometer, and the image sensor as input data, and
• wherein the operation method further comprises, when a first estimation result obtained by using the first pattern recognition algorithm and a second estimation result obtained by using the second pattern recognition algorithm have a same format, determining a final estimation result as a weighted sum of the first estimation result and the second estimation result.

An object recognition apparatus comprising:

• a first spectrometer configured to obtain a first type of spectrum data from light scattered, emitted, or reflected from an object;
• a second spectrometer configured to obtain a second type of spectrum data from the light scattered, emitted, or reflected from the object, the second type of spectrum data being different from the first type of spectrum data;
• and
• a processor configured to identify the object using a first pattern recognition algorithm that uses the first type of spectrum data as input data and a second pattern recognition algorithm that uses the second type of spectrum data as input data,
• wherein the processor is further configured to, when a first estimation result obtained by using the first pattern recognition algorithm and a second estimation result obtained by using the second pattern recognition algorithm have a same format, determine a final estimation result as a weighted sum of the first estimation result and the second estimation result.

An object recognition apparatus comprising:

• a spectrometer configured to obtain spectrum data from light scattered, emitted, or reflected from an object;
• an image sensor configured to obtain image data of the object;
• and
• a processor configured to identify the object using a first pattern recognition algorithm that uses the spectrum data as input data and a second pattern recognition algorithm that uses the image data as input data,
• wherein the processor is further configured to, when a first estimation result obtained by using the first pattern recognition algorithm and a second estimation result obtained by using the second pattern recognition algorithm have a same format, determine a final estimation result as a weighted sum of the first estimation result and the second estimation result.