1. 1 Book Cover Recognition SHAO-CHUAN (SHAWN) WANG CMOS E6737 Biometrics Final Project sw2644@columbia.edu http://shaochuan.info/
2. Book Cover Recognition System Goal: Input: A middle resolution image taken from web camera or cell phone (640 x 480) that contains a book. Output: The book title/id. 2 Book Cover Recognition System “Learning from Data”
3. Baseline Model: Bag-of-words Low level feature extraction (Dense SIFT) (CVPR09) Visual words learning (a.k.a codebook learning) via vector quantization. Spatial pooling of local features. Linear SVM classification. (libLinear package) 3
4. A Glance on Dataset (1/2) 9 books. training on half (15), test on half (15): 4
6. Baseline: Experiments System parameters: 15 training images per book, test on the rest. Resize image size to 300 pixels (long side) Visual codebook size (K = 225) # of spatial pyramid level = 0,1,2 Spatial pooling function = max L2-regularized 1-norm loss linear SVM 5-fold cross validation Results: Nearly perfect recognition results. (99.259%=134/135) 6