Habibollah Agh Atabay

Gonbad Kavous University | GPNU · Department of Computer

Several generalizations of Shannon entropy have been introduced in the literature. One of such a measure is the cumulative residual Tsallis entropy (CRTE) which can be viewed as an alternative dispersion measure. In this paper, we obtain some further results for such a measure, in relation with the cumulative residual Tsallis entropy and with the v...

Recognition of specific types of objects and entities in images has been among the research interests for a long time. In animal species recognition in still images, horse breeds identification has not yet been investigated. In this paper, the identification of horse breeds in natural scene images is addressed. Since a publicly available horse bree...

Deep Learning for plant leaf analysis has been recently studied in various works. In most cases, Transfer Learning has been utilized, where the weights of networks, which are stored in the pre-trained models, are fine-tuned to use in the considered task. In this paper, Convolutional Neural Networks (CNNs), are employed to classify tomato plant leaf...

Sketch-based object recognition and classification has become an important research topic in vision applications. In the recent years, Convolutional Neural Networks (CNNs), have emerged as a powerful framework for feature representation and recognition for variety of applications in image analysis. But there exists few works that utilized CNNs in s...

Recognizing objects by their shapes, has been an interesting problem in image understanding, and has attracted researchers’ attention. The superiority of Convolutional Neural Networks (CNNs) in various object recognition tasks have been proven in recent years. But CNNs has been rarely used in binary shape classification. In this paper, a CNN archit...

In this research, an application of Convolutional Neural Networks (CNNs) on the task of leaf classification is presented. Nowadays, CNNs have become well known methods in object recognition to generate learned feature representations and classification, and gradually have been dominating on various image domains. There exists few works that applied...

Feature selection is an important step in Content Based Image Retrieval (CBIR) which has a great impact on reducing complexity and increasing efficiency of CBIR frameworks. Swarm Intelligence (SI) methods, as effective optimization techniques, has been used to solve variety of problems. In this paper, a CBIR framework is established to retrieve gra...

Feature selection is an effective tool to improve the performance of content based image retrieval systems. This paper presents an effective moment weighting method according to image reconstruction and retrieval accuracyto reduce the dimensionality of moment-based features. Weighting algorithms are important group of feature selection schemes. Amo...

Clustering data are one of the key issues in data mining that has attracted much attention. One of the famous algorithms in this field is K-Means clustering that has been successfully applied to many problems. But this method has its own disadvantages, such as the dependence of the efficiency of this method to initialization of cluster centers. To...

Content based image retrieval systems usually extract low level features to retrieve similar images. But in most cases, selection of suitable features according to their impact on the classification accuracy has been less considered. This paper studies the effects of reducing the number of features and selecting the most effective subset of feature...