For the traffic sign recognition test, the traffic sign recognition user interface named Traffic Sign Recognizer (TSR) is developed. The new GUI for traffic sign recognition is being built on top of the polygon detection algorithm that I introduced at Traffic sign feature extraction. The manual region selection function is additionally introduced. Below screen shot shows one example that TSR recognized the school warning sign successfully.
Image:tspr_extracted_region_after_boundary_removal.png|Extracted region after boundary removal Image:tspr_resized_image.png|Resize image to 200x200 Image:tspr_colordecomposition.png|Re-sample colors into 7 main traffic sign colors Image:tspr_binarization.png|Binarization for the line crossing state generation
The summary of the recognition algorithm is following. Once a polygon of interests is selected. The region of interests is extracted from the image by classifying the background (repainted with the background color) and foreground (traffic sign area). After, it is resized to 200x200 for the normalized line cross checking. Since the number of colors used in the traffic signs are limited, we perform the color decomposition. Finally, the target image is binarized based on the computation of its dominant color as the background color and others as foreground colors. This binarized image is used for computing the line crossing states.