Automatic Image Annotation Using SURF Descriptors

In recent years there is an apparent shift in research from content based image retrieval (CBIR) to automatic image annotation in order to bridge the gap between low level features and high level semantics of images. Automatic Image Annotation (AIA) techniques facilitate extraction of high level semantic concepts from images by machine learning techniques. Many AIA techniques use feature analysis as the first step to identify the objects in the image. However, the high dimensional image features make the performance of the system worse. This paper describes and evaluates an automatic image annotation framework which uses SURF descriptors to select right number of features and right features for annotation. The proposed framework uses a hybrid approach in which k-means clustering is used in the training phase and fuzzy K-NN classification in the annotation phase. The performance of the system is evaluated using standard metrics.

Analysis of resource use efficiency of the spinning mills in Kerala

This thesis discusses the factors which influence the productive and financial performance of the spinning mills in Kerala. The study will also help to assess the effect of ongoing reforms in the industrial sector in India. The main objective of the study is to identify and analyse the factors affecting the efficiency of the spinning mills. The unique feature of the study is that it compares the performance of private sector in relation to its public counterparts and also performance of small sector in relation to medium sector. The study is carried out with reference to the relative performance of differmills in Kerala and to identify the sources of differences in performance. The study covers twenty one spinning mills in Kerala, of which ten are in the private sector, four under NTC, three under co—operat;ive sector and four under KSTC.Measured in terms of firm-size fifteen belong to small size with a spindleage of less than 26,000 and six are in the medium size with a spindleage of 26,000 to 50,0OO.1 The period of study is 1982-83 to 1991-92. Hence, only those companies, of which data of 10 years upto 1991-92 wereavailable, are taken for study.