Systems and methods for image preprocessing to improve accuracy of object recognition
The present disclosure relates to image preprocessing to improve object recognition. In one implementation, a system for preprocessing an image for object recognition may include at least one memory storing instructions and at least one processor configured to execute the instructions to perform operations. The operations may include receiving the image, detecting a plurality of bounding boxes within the image, grouping the plurality of bounding boxes into a plurality of groups such that bounding boxes within a group have shared areas exceeding an area threshold, deriving a first subset of the plurality of bounding boxes by selecting bounding boxes having highest class confidence scores from at least one group, selecting a bounding box from the first subset having a highest score based on area and class confidence score, and outputting the selected bounding box.
1. A system for preprocessing an image for object recognition, the system comprising:
at least one memory storing instructions; and
at least one processor configured to execute the instructions to perform operations comprising:
receiving the image,
detecting a plurality of bounding boxes within the image,
grouping the plurality of bounding boxes into a plurality of groups, wherein bounding boxes within a group have shared areas exceeding an area threshold,
deriving a first subset of the plurality of bounding boxes by selecting bounding boxes having highest class confidence scores from at least one group,
further deriving a second subset of bounding boxes, by selecting:
each of the bounding boxes selected in the second subset having combined scores above a threshold, and
no bounding boxes being selected in the second subset if no bounding box has a combined score is above the threshold,
wherein the combined scores are determined by each bounding box's area and class confidence score.
2. The system of claim 1 , wherein the operations further comprise paring the first subset by eliminating bounding boxes that do not include a center point of the image.
3. The system of claim 2 , wherein the selected bounding boxes are selected from the pared first subset.
4. The system of claim 1 , wherein the operations further comprise deriving a third subset of the plurality of bounding boxes by eliminating bounding boxes having one or more class confidence scores below a second class confidence score threshold.
5. The system of claim 4 , wherein each bounding box has a plurality of class confidence scores, and the third subset is derived by eliminating bounding boxes for which each class confidence score is below the second class confidence score threshold.
6. The system of claim 4 , wherein the first subset is derived from the third subset.
7. The system of claim 1 , wherein the operations further comprise deriving a third subset of the plurality of bounding boxes by eliminating bounding boxes having a highest class confidence score not within a selected class.
8. The system of claim 1 , wherein the operations further comprise cropping the image based on at least one selected bounding box.
9. The system of claim 8 , wherein cropping the image comprises cropping the image to include pixels enclosed by the at least one selected bounding box and pixels located within a threshold of the at least one selected bounding box.
10. The system of claim 9 , wherein the threshold comprises 10% of a corresponding dimension of the at least one selected bounding box.
11. A system for preprocessing an image for object recognition, the system comprising:
at least one memory storing instructions; and
at least one processor configured to execute the instructions to perform operations comprising:
receiving the image having dimensions,
resizing the image to match input dimensions of a model,
using the model, detecting a plurality of bounding boxes within the resized image,
grouping the plurality of bounding boxes into a plurality of groups, wherein bounding boxes within a group have shared areas exceeding an area threshold,
deriving a first subset of the plurality of bounding boxes by selecting bounding boxes having a highest class confidence scores from at least one group,
further deriving a second subset by selecting a plurality of bounding boxes having combined scores above a threshold,
selecting no bounding boxes if no combined score is above the threshold,
wherein the combined scores are determined by each bounding box's area and class confidence score,
scaling the selected bounding boxes based on the dimensions of the received image and the input dimensions.
12. The system of claim 11 , wherein the operations further comprise paring the first subset by eliminating bounding boxes that do not include a center point of the image.
13. The system of claim 12 , wherein the selected bounding boxes are selected from the pared first subset.
14. The system of claim 11 , wherein the operations further comprise deriving a third subset of the plurality of bounding boxes by eliminating bounding boxes having one or more class confidence scores below a second class confidence score threshold.
15. The system of claim 11 , wherein the operations further comprise cropping the image based on at least one scaled bounding box.
16. The system of claim 15 , wherein cropping the image comprises overlaying the scaled bounding box on the image and cropping the image to include pixels enclosed by the overlaid bounding box and pixels located within a threshold of the overlaid bounding box.
17. The system of claim 16 , wherein the threshold comprises 10% of a corresponding dimension of the at least one bounding box.
18. The system of claim 15 , wherein the cropped image is input to an object recognition algorithm.
19. The system of claim 18 , wherein the object recognition algorithm comprises a convolutional neural network.
20. A system for preprocessing an image for object recognition, the system comprising:
at least one memory storing instructions; and
at least one processor configured to execute the instructions to perform operations comprising:
receiving the image having dimensions,
resizing the image to match input dimensions of a model,
using the model, detecting a plurality of bounding boxes within the resized image,
deriving a first subset of the plurality of bounding boxes by eliminating bounding boxes having a highest class confidence score below a first class confidence score threshold,
deriving a second subset of the first subset by eliminating bounding boxes having a highest class confidence score not within a selected class,
grouping the bounding boxes of the second subset into a plurality of groups, wherein bounding boxes within a group have shared areas exceeding an area threshold,
deriving a third subset of the second subset by selecting bounding boxes having combined scores above a threshold,
selecting a bounding box having a highest class confidence score from at least one group if no combined score is above the threshold,
wherein the combined scores are determined by each bounding box's area and class confidence score
paring the third subset by eliminating bounding boxes that do not include a center point of the image,
selecting a bounding box from the pared third subset, the selected bounding box having a highest score based on area and class confidence score,
scaling the selected bounding box based on the dimensions of the received image and the input dimensions, and
outputting the scaled bounding box.