Revision history [back]

forget cascade classifiers (for the classification, as they can only handle a single class, while you got many).

also forget any features2d matching (again, for the classification part, as the matching part of this was never made for that purpose. (maybe BOW & SVM, but not Flann or BF matcher)

cnn's will do a grat job at classification, but you have to feed them with cropped patches of potential candidates, so, for a typical large image, you would still need some detection/cropping process in front of that.

there are cnns like RCNN and YOLO, which are able to do object segmentation and classification at the same time, quite advanced, and not at all covered from opsncv atm, unfortunately.

forget cascade classifiers (for the classification, as they can only handle a single class, while you got many).

also forget any features2d matching (again, for the classification part, as the matching part of this was never made for that purpose. (maybe BOW & SVM, but not Flann or BF matcher)

cnn's will do a grat job great job at classification, but you have to feed them with cropped patches of potential candidates, so, for a typical large image, you would still need some detection/cropping process in front of that.

there are cnns like RCNN and YOLO, which are able to do object segmentation and classification at the same time, quite advanced, and not at all covered from opsncv opencv atm, unfortunately.

forget cascade classifiers (for the classification, as they can only handle a single class, while you got many).

also forget any features2d matching (again, for the classification part, as the matching part of this was never made for that purpose. (maybe BOW & SVM, but not Flann or BF matcher)

cnn's will do a great job at classification, but you have to feed them with cropped patches of potential candidates, so, for a typical large image, you would still need some detection/cropping process in front of that.that (maybe you can train a cascade for detecting all speed limits).

there are cnns like RCNN and YOLO, which are able to do object segmentation and classification at the same time, quite advanced, and not at all covered from opencv atm, unfortunately.

(and yes, use color !)

forget cascade classifiers (for the classification, as they can only handle a single class, while you got many).

also forget any features2d matching (again, for the classification part, as the matching part of this was never made for that purpose. (maybe BOW & SVM, but not Flann or BF matcher)

cnn's will do a great job at classification, but you have to feed them with cropped patches of potential candidates, so, for a typical large image, you would still need some detection/cropping process in front of that (maybe you can train a cascade for detecting all speed limits).

there are cnns like RCNN RCNN and YOLO, YOLO, which are able to do object segmentation and classification at the same time, quite advanced, and not at all covered from opencv atm, unfortunately.

(and yes, use color !)

forget cascade classifiers (for the classification, as they can only handle a single class, while you got many).

also forget any features2d matching (again, for the classification part, as the matching part of this was never made for that purpose. (maybe BOW & SVM, but not Flann or BF matcher)

cnn's cnn's will do a great job at classification, but you have to feed them with cropped patches of potential candidates, so, for a typical large image, you would still need some detection/cropping process in front of that (maybe you can train a cascade for detecting all speed limits).

there are cnns like RCNN and YOLO, which are able to do object segmentation and classification at the same time, quite advanced, and not at all covered from opencv atm, unfortunately.

(and yes, use color !)

forget cascade classifiers (for the classification, as they can only handle a single class, while you got many).

also forget any features2d matching (again, for the classification part, as the matching part of this was never made for that purpose. (maybe BOW & SVM, but not Flann or BF matcher)

cnn's will do a great job at classification, but you have to feed them with cropped patches of potential candidates, so, for a typical large image, you would still need some detection/cropping process in front of that (maybe you can train a cascade for detecting all speed limits).

there are cnns like RCNN and YOLO, which are able to do object segmentation and classification at the same time, quite advanced, and not at all covered from opencv atm, unfortunately.

(and yes, use color !)

forget cascade classifiers (for the classification, as they can only handle a single class, while you got many).

also forget any features2d matching (again, for the classification part, as the matching part of this was never made for that purpose. (maybe BOW & SVM, but not Flann or BF matcher)

cnn's will do a great job at classification, but you have to feed them with cropped patches of potential candidates, so, for a typical large image, you would still need some detection/cropping process in front of that (maybe you can train a cascade for detecting all speed limits).

there are cnns like RCNN and YOLO, which are able to do object segmentation and classification at the same time, quite advanced, and not at all covered from opencv atm, unfortunately.

(and yes, use color !)

forget cascade classifiers (for the classification, as they can only handle a single class, while you got many).

also forget any features2d matching (again, for the classification part, as the matching part of this was never made for that purpose. (maybe BOW & SVM, but not Flann or BF matcher)

cnn's will do a great job at classification, but you have to feed them with cropped patches of potential candidates, so, for a typical large image, you would still need some detection/cropping process in front of that (maybe you can train a cascade for detecting all speed limits).that.

there are cnns like RCNN and YOLO, which are able to do object segmentation and classification at the same time, quite advanced, and not at all covered from opencv atm, unfortunately.

(and yes, use color !)