Abstract
Using multiple feature descriptors simultaneously increases the accuracy of object recognition. Usage of dynamic coefficients, in other words, non-identical and proportional to the importance of each descriptor for each class, is an appropriate and efficient way to combine different feature descriptors. In this paper, a new and efficient structure is proposed that calculates these coefficients using the sparse representation classifier. For each feature descriptor, we propose an important criterion based on the reconstruction error of the images via the sparse representation. The assigned importance of each descriptor for each class is different and calculated based on the reconstruction errors of the images when only their classmate images contribute in the reconstruction process. In addition, an innovative method is proposed which can be used to help classes that are not well described by any descriptor as well. In this method, using the residual criteria, these classes are identified and using a defined notion of similarity among classes, the accuracy of these classes with the support of the similar ones is enhanced. The experimental results of the proposed work on Caltech-101 and Caltech-256 databases show the success of approaches compared with state-of-the-art ones on the same databases.
Similar content being viewed by others
References
Aharon M, Elad M, Bruckstein AM (2005) K-SVD and its non-negative variant for dictionary design. In: Proceedings of the SPIE conference wavelets, vol 5914
Aharon M, Elad M, Bruckstein A (2006) K-SVD: an algorithm for designing overcomplete dictionaries for sparse representation. IEEE Trans Signal Process 54(11):4311–4322
Boureau Y, Bach F, LeCun Y, Ponce J (2010) Learning mid-level features for recognition. In: International conference on computer vision pattern recognition (CVPR), pp 2559–2566
Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273–297
Crandall D, Felzenszwalb P, Huttenlocher D (2007) Object recognition by combining appearance and geometry. Toward Category-Level Object Recogn 4170:462–482
Dosovitskiy A, Fischer P, Springenberg JT, Riedmiller M, Brox T (2016) Discriminative unsupervised feature learning with exemplar convolutional neural networks. IEEE Trans Pattern Anal Mach Intell 38(9):1734–1747
Elad M, Aharon M (2006) Image denoising via learned dictionaries and sparse representation. Int Conf Comput Vis Pattern Recogn 1:895–900
Everingham M, Van Gool L, Williams CKI, Winn J, Zisserman A, (2008) The PASCAL visual object classes challenge 2008 (VOC2008) results. http://www.pascalnetwork.org/challenges/VOC/voc2008/workshop/index.html
Fei-Fei L, Fergus R, Perona P (2004) Learning generative visual models from few training examples: an incremental bayesian approach tested on 101 object categories. In: International conference on computer vision pattern recognition. Workshop on generative-model based vision, pp 59–70
Fergus R, Perona P, Zisserman A (2003) Object class recognition by unsupervised scale-invariant learning. Int Conf Comput Vis Pattern Recogn 56:968
Ferrari V, Tuytelaars T, Gool LV (2004) Simultaneous object recognition and segmentation by image exploration. Proc Eighth Eur Conf Comput Vis 56:963
Gao S, Tsang IW, Chia LT, Zhao P (2010) Local features are not lonely-laplacian sparse coding for image classification. In: International conference on computer vision pattern recognition (CVPR), pp 3555–3561
Goh H, Thome N, Cord M, Lim JH (2014) Learning deep hierarchical visual feature coding. IEEE Trans Neural Netw Learn Syst 25(12):2212–2225
Griffin G, Holub A, Perona P (2007) Caltech-256 object category dataset, Technical Report 7694
Guermeur Y (2002) Combining discriminant models with new multi-class SVMs. Pattern Anal Appl 5(2):168–179
Guermeur Y (2013) Combining multi-class SVMs with linear ensemble methods that estimate the class posterior probabilities. Stoch Model Tech Data Anal Int Conf 42(16):3011–3030
Gui J, Liu T, Tao D, Sun Z, Tan T (2015) Representative vector machines: a unified framework for classical classifiers. IEEE Trans Cybern 99:210
Hajigholam MH, Raie AA, Faez K (2016) Multitask joint spatial pyramid matching using sparse representation with dynamic coefficients for object recognition. J Electron Imaging 25(2):569
Han H, Han Q, Li X, Gu J (2013) Hierarchical spatial pyramid max pooling based on SIFT features and sparse coding for image classification. IET Comput Vis 7(2):144–150
Hong LK, Haur TY, Loong LF (2017) Aggregate of HMAXs for image classification. In: International conference on advances in electrical, electronic and systems engineering (ICAEES), pp 366–370
Horng G, Liu MX, Chen CC (2020) The smart image recognition mechanism for crop harvesting system in intelligent agriculture. IEEE Sens J 20(5):2766–2781
Huang K, Wang C, Tao D (2015) Learning high-order topology of visual words in feature encoding for image classification. Trans Image Process 24(11):3598–3608
Jiang S, Min W, Liu L, Luo Z (2019) Multi-scale multi-view deep feature aggregation for food recognition. IEEE Trans Image Process 29:265–276
Karmakar P, Teng SW, Lu G, Zhang D (2020) An enhancement to the spatial pyramid matching for image classification and retrieval. IEEE Access 8:22463–22472
Kennedy J, Eberhart R (1995) Particle swarm optimization. Proc IEEE Int Conf Neural Netw 4:1942–1948
Lan X, Zitnick C, Szeliski R (2007) Local bi-gram model for object recognition MSR-TR-2007-54. Technical Report, Microsoft Research
Lazebnik S, Schmid C, Ponce JA (2005) Maximum entropy framework for part-based texture and object recognition. In: IEEE international conference on computer vision (ICCV), vol 1
Lazebnik S, Schmid C, Ponce J (2006) Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. Int Conf Comput Vis Pattern Recogn 2:2169–2178
Lee DD, Seung HS (1999) Learning the parts of objects by non-negative matrix factorization. Nature 401(6755):788–791
Lee H, Battle A, Raina R, Ng AY (2006) Efficient sparse coding algorithms. In: NIPS
Leibe B, Leonardis A, Schiele B (2004) Combined object categorization and segmentation with an implicit shape model. Proc ECCV Workshop Stat Learn Comput Vis 75:8644
Ling H, Soatto S (2007) Proximity distribution kernels for geometric context in category recognition. In: International conference on computer vision (ICCV)
Liu D, Hua G, Viola P, Chen T (2008) Integrated feature selection and higher-order spatial feature extraction for object categorization. In: International conference on computer vision pattern recognition (CVPR)
Lowe D (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91–110
Nguyen HV, Patel VM (2014) Max residual classifier. IEEE Appl Comput Vis 98:580–587
Olshausen BA, Field DJ (1996) Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature 381(6583):607–609
Rouhafzay G, Cretu A (2020) Object recognition from haptic glance at visually salient locations. IEEE Trans Instrum Measur 69(3):672–682
Shao L, Liu L, Li X (2017) Feature learning for image classification via multiobjective genetic programming. IEEE Trans Neural Netw Learn Syst 25(7):1359–1371
Shechtman E, Irani M (2007) Matching local self-similarities across images and videos. Int Conf Comput Vis Pattern Recogn 2:13–21
Shen B, Zhang YJ (2009) Foreground segmentation via sparse representation. IEEE Int Conf Syst Man Cybern 56:887
Si J, Zhang H, Li CG, Guo J (2017) Spatial pyramid-based statistical features for person re-identification: a comprehensive evaluation. IEEE Trans Syst Man Cybern Syst 48(7):1140–1154
Van de Sande K, Gevers T, Snoek C (2010) Evaluating color descriptors for object and scene recognition. IEEE Trans Pattern Anal Mach Int 32(9):1582–1596
Wei T, Chen CW, Wang C (2016) Barycentric coordinates based soft assignment for object classification. In: IEEE International conference on multimedia and expo workshops (ICMEW), pp 1–6
Wright J, Yang A, Ganesh A, Sastry S, Ma Y (2009) Robust face recognition via sparse representation. IEEE Trans Pattern Anal Mach Intell 31(2):210–226
Yang J, Yang MH (2012) Top-down visual saliency via joint CRF and dictionary learning.In: International conference on computer vision pattern recognition (CVPR), pp 2296–2303
Yang J, Yu K, Gong Y, Huang T (2009) Linear spatial pyramid matching using sparse coding for image classification. In: International conference on computer vision pattern recognition (CVPR), pp 1794–1801
Yang M, Zhang L, Zhang D, Wang S (2012) Relaxed collaborative representation for pattern classification. In: IEEE conference on computer vision pattern recognition (CVPR), pp 2224–2231
Yoon J, Choi J, Yoo CD (2015) A hierarchical-structured dictionary learning for image classification. IEEE international conference on imaging proceedings (ICIP), pp 155–159
Yu K, Lin Y, Lafferty J (2011) Learning image representations from the pixel level via hierarchical sparse coding. In: International conference on computer vision pattern recognition (CVPR), pp 1713–1720
Yuan X, Yan S (2010) Visual classification with multi-task joint sparse representation. In: International conference on computer vision pattern recognition (CVPR), pp 3493–3500
Zeng J, Liu M, Fu X, Ruiyu G, Leng L (2019) Curvature bag of words model for shape recognition. IEEE Access 7:57163–57171
Zhang Y, Chen T (2009) Efficient Kernels for identifying unbounded-order spatial features. In: International conference on computer vision pattern recognition (CVPR)
Zuo Y, Zhang B (2011) Robust hierarchical framework for image classification via sparse representation. J Tsinghua Sci Technol 16(1):13–21
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Rights and permissions
About this article
Cite this article
Hajigholam, Mh., Raie, AA. & Faez, K. Using Sparse Representation Classifier (SRC) to Calculate Dynamic Coefficients for Multitask Joint Spatial Pyramid Matching. Iran J Sci Technol Trans Electr Eng 45, 295–307 (2021). https://doi.org/10.1007/s40998-020-00351-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40998-020-00351-3