The Present paper compares the texture features based on co-occurrence and the new Matrix-method called "Qmatrix", which measures the similarities of grey levels. The problem addressed is to determine which features optimize classification rate. Such features may be used in image segmentation, compression and in evaluation of statistical features. Though Q-Matrix is a new method for evaluating similarity measures, but large scale objective comparison has not been performed in the past. The main objective of this paper is to compare and evaluate statistical feature parameters on both the methods. Two types of textures are studied. The Experimental result indicates the good classification results for Q-matrix.
Keywords: Co-occurrence features, Q-Matrix, texture features, Similarity measures, Statistical Features
[...] PERFORMANCE EVALUATION OF TEXTURE FEATURES WITH CO-OCCURRENCE AND Q-MATRIX ABSTRACT: The Present paper compares the texture features based on co-occurrence and the new Matrix-method called which measures the similarities of grey levels. The problem addressed is to determine which features optimize classification rate. Such features may be used in image segmentation, compression and in evaluation of statistical features. Though Q-Matrix is a new method for evaluating similarity measures, but large scale objective comparison has not been performed in the past. [...]
[...] A graph of Q-matrix with Small no of emphasis and Large no of emphasis. Q-MATRIX Entropy S econdary Movem ent Leather Betel Fig.2. A graph of matrix with Entropy and secondary movement. Q-MATRIX 2500 No of non uniformity Small no of emphasis Leather Betel Co-Occurence Matrix E n tr o p y 20000 Leather 15000 Betel Contrast Fig.3. A graph of Q-matrix with Small no of emphasis and No of non uniformity. Fig.6. A graph of Co-Occurrence matrix with Contrast and Entropy CONCLUSIONS. [...]
APA Style reference
For your bibliographyOnline reading
with our online readerContent validated
by our reading committee
