摘要：Content Based Image Retrieval (CBIR) system is an efficient searchengine which has the potentiality of retrieving the images from huge repositoriesby extracting the visual features. It includes color, texture and shape. Texture isthe most eminent feature among all. This investigation focuses upon theclassification complications that crop up in case of big datasets. In this, texturetechniques are explored with machine learning algorithms in order to increasethe retrieval efficiency. We have tested our system on three texture techniquesusing various classifiers which are Support vector machine, K-NearestNeighbor (KNN), Naïve Bayes and Decision Tree (DT). Variant evaluationmetrics precision, recall, false alarm rate, accuracy etc. are figured out tomeasure the competence of the designed CBIR system on two benchmarkdatasets, i.e. Wang and Brodatz. Result shows that with both these datasets theKNN and DT classifier hand over superior results as compared to others.
