Postgraduate Students: Vladimír Arnot, Daniel Čapek, Rudolf Čejka, Dao Minh, Tomá Dulík, Martin Hrubý, Radek Kočí, Petr Kotásek, Marek Křejpský, Bohuslav Křena, Vladislav Kubíček, Vladimír Marek, Petr Matouek, Ale Mičín, Jiří Očenáek, Tomá Ondráček, Petr Peňás, Jaroslav Ráb, Richard Růička, Luká Sekanina, Ivan Schwarz, Azedien Sllame, Petr Smolík, Jiří Staroba, Josef Strnadel, Luká Szemla, Pavel Tinovský, Michal Tomů, Milan Urbáek, Michal Vojkůvka, Petr Vurm, Frantiek Zbořil

Department of Computer Science and Engineering

Adopting effective model to access the desired images is essential nowadays with the presence of a huge amount of digital images. The present paper introduces an accurate and rapid model for content based image retrieval process depending on a new matching strategy. The proposed model is composed of four major phases namely: features extraction, dimensionality reduction, ANN classifier and matching strategy. As for the feature extraction phase, it extracts a color and texture features, respectively, called color co-occurrence matrix (CCM) and difference between pixels of scan pattern (DBPSP). However, integrating multiple features can overcome the problems of single feature, but the system works slowly mainly because of the high dimensionality of the feature space. Therefore, the dimensionality reduction technique selects the effective features that jointly have the largest dependency on the target class and minimal redundancy among themselves. Consequently, these features reduce the calculation work and the computation time in the retrieval process. The artificial neural network (ANN) in our proposed model serves as a classifier so that the selected features of query image are the input and its output is one of the multi classes that have the largest similarity to the query image. In addition, the proposed model presents an effective feature matching strategy that depends on the idea of the minimum area between two vectors to compute the similarity value between a query image and the images in the determined class. Finally, the results presented in this paper demonstrate that the proposed model provides accurate retrieval results and achieve improvement in performance with significantly less computation time compared with other models.

A new matching strategy for content based image retrieval system

This paper presents a content-based image retrieval technique that focuses on extraction and reduction in multiple features. To obtain multi-level decomposition of the image by extracting approximation and correct coefficients, discrete wavelet transformation is applied to the RGB channels initially. Therefore, both approximation and correct coefficients are applied to the dominant rotated local binary pattern termed as texture descriptor which is computationally effective and rotationally invariant. For a local neighbor patch, a rotation invariance function image is obtained by measuring the descriptor relative to the reference. The proposed approach contains the complete structural information extracted from the local binary patterns and also extracts the additional information using the information of magnitude, thereby achieving extra discriminative power. Then, GLCM description is used by obtaining the dominant rotated local binary pattern image to extract the statistical characteristics for texture image classification. The proposed technique is applied to CORAL dataset with the help of particle swarm optimization-based feature selector to minimize the number of features that can be used during the classification process. The three classifiers, i.e., support vector machine, K-nearest neighbor, and decision tree, are trained and tested. The comparison is based in terms of Accuracy, precision, recall, and F-measure performance metrics for classification. Experimental results show that the proposed approach achieves better accuracy, precision, recall, and F-measure values for most of the CORAL dataset classes.

A novel content-based image retrieval approach for classification using GLCM features and texture fused LBP variants

Information fusion in content based image retrieval

Food Track & Trace ontology for helping the food traceability control

Content-based image retrieval using color and texture fused features

Representing and organizing knowledge is important for a semantic knowledge searching system. To implement vegetable supply chain knowledge searching, we build three Ontologies on the base of our investigation: the vegetable supply chain domain Ontology, the user Ontology and the knowledge content Ontology. And meantimes, a metadata model is set up. we integrate these Ontologies and metadata model together by setting up the relationships of these classes. Finally we formalize the metadata by RDF (Resource Description Framework) and implement the searching system on the knowledge database of vegetable supply chain. Through the semantic searching, the users can get more suitable knowledge of vegetable supply chain.

Ontology-based Vegetable Supply Chain Knowledge Searching System

Since ontology was put forward by Neches and Fikes in 1991, the research on ontology is becoming increasingly matured after more than 10 years development. Although usages on concepts and terms related with ontology do not keep completely identical, the agreement of actual use has emerged. Most researches are concentrated on theoretic in current ontology research, while practical application of ontology is still less. Ontology takes the role as a philosophical concept originally, which regarded as an explanation or description to an objective existing system from the philosophy category, and concerns the abstract nature of the objective reality. Later, it is given a new definition by the artificial intelligence category with the development of artificial intelligence. Neches and Fikes (1991) define ontology as the “explicit formal specifications of the terms in the domain and relations among them”. The terms and relations are abstract description of phenomenon happened in the word. Gruber (1993) gives a most popular definition to ontology:”ontology is the clear specification on a conceptual model”. Based on this definition, another new concept of ontology is given by Borst, i.e. (1997) as “ontology is the clear specification on a sharing conceptual model”. Studer (1998) thinks that ontology consists of four layers meaning after an in-depth studying on the two above definitions, which are “conceptualization”, “explicit”, “formal” and “share”. Conceptualization refers to models obtained by abstracting some related phenomenon in the objective world, which performs independent of the specific state of the environment. Explicit refers to explicit definitions to used concepts and their restriction. Formal refers to the ontology model can be processed by computer. Share refers to ontology aims at group consensus instead of individual consensus. The ontology goal is to capture the knowledge of relevant domain, provide a common understanding to the knowledge, confirm vocabularies of the domain and define the relationships between the vocabularies clearly. Some scholars regard ontology as an approach to construct knowledge base. There are different ontology category modes according to different ontology attributes. Gruber (1993) divides ontology into four classes as its level of detail and level of dependence: top level

Jun Yue

Papers

Content-based image retrieval using color and texture fused features

Ontology-based Vegetable Supply Chain Knowledge Searching System

Ontology and Its Application in Supply Chain Information Management