The Image Classification with Different Types of Image Features

In this paper we present a modified Bag-of-Words algorithm used in image classification. The classic Bag-of-Words algorithm is used in natural language processing. A text (such as a sentence or a document) is represented as a bag of words. In image retrieval or image classification this algorithm also works on one characteristic image feature and most often it is a descriptor defining the surrounding of a keypoint obtained by using e.g. the SURF algorithm. The modification which we have introduced involves using two different types of image features – the descriptor of a keypoint and also the colour histogram, which can be obtained from the surrounding of a keypoint. This additional feature will make it possible to obtain more information as the commonly used SURF algorithm works only on images with greyscale intensity. The experiments which we have conducted show that using this additional image feature significantly improves image classification results by using the BoW algorithm.

[1]  Pietro Perona,et al.  Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[2]  Bogdan M. Wilamowski,et al.  Parallel Learning of Feedforward Neural Networks Without Error Backpropagation , 2016, ICAISC.

[3]  Piraveenan Mahendra,et al.  Evolutionary Stable Strategies In Networked Games: The Influence Of Topology , 2015, J. Artif. Intell. Soft Comput. Res..

[4]  Janusz T. Starczewski.  Advanced Concepts in Fuzzy Logic and Systems with Membership Uncertainty , 2013, Studies in Fuzziness and Soft Computing.

[5]  Gabriela Csurka,et al.  Visual categorization with bags of keypoints , 2002, eccv 2004.

[6]  Marcin Woźniak,et al.  Graphic object feature extraction system based on Cuckoo Search Algorithm , 2016, Expert Syst. Appl..

[7]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[8]  Adam Krzyzak,et al.  A Modification of the Silhouette Index for the Improvement of Cluster Validity Assessment , 2016, ICAISC.

[9]  Marcin Korytkowski,et al.  Query-by-Example Image Retrieval in Microsoft SQL Server , 2016, ICAISC.

[10]  Marcin Wozniak.  Novel Image Correction Method Based on Swarm Intelligence Approach , 2016, ICIST.

[11]  Marcin Korytkowski,et al.  Novel visual information indexing in relational databases , 2017, Integr. Comput. Aided Eng..

[12]  Marcin Zalasinski,et al.  New Algorithm for On-line Signature Verification Using Characteristic Hybrid Partitions , 2015, ISAT.

[13]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[14]  Alexei A. Efros,et al.  Discovering objects and their location in images , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[15]  Pietro Perona,et al.  A Bayesian hierarchical model for learning natural scene categories , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[16]  Andreas Rauber,et al.  The growing hierarchical self-organizing map , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[17]  Maria do Carmo Nicoletti,et al.  Enhancing Constructive Neural Network Performance Using Functionally Expanded Input Data , 2016, J. Artif. Intell. Soft Comput. Res..

[18]  Cécile Barat,et al.  Fusion of tf.idf weighted bag of visual features for image classification , 2010, 2010 International Workshop on Content Based Multimedia Indexing (CBMI).

[19]  Eugene Semenkin,et al.  Multi-Objective Heuristic Feature Selection for Speech-Based Multilingual Emotion Recognition , 2016, J. Artif. Intell. Soft Comput. Res..

[20]  Marcin Wozniak,et al.  On manipulation of initial population search space in heuristic algorithm through the use of parallel processing approach , 2016, 2016 IEEE Symposium Series on Computational Intelligence (SSCI).

[21]  Cordelia Schmid,et al.  Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).