Abstract: Image annotation is a task of assigning a set of semantic tags or keywords to unlabeled image based on a training set of data. This machine learning process depends on extraction and clustering the low-level features of images then mapping them to the semantic which is high-interest image retrieval. Many annotation techniques with reasonable performance have proposed in the last decade. The proposed algorithm for automatic annotation in this paper depends on similarity computation and label transferring to the query image. Similarity computing uses low-level image features and significant distance estimates. The feature vector of the test image compared with the feature matrix of similar and dissimilar image pairs in the training data sets. Then the label or keyword transfer from the similar image pair to the test image is performed by counting the local frequency of neighbor’s keywords. Performance is evaluated using precision and recall.

• Publication Date: 16-Dec-2016
• DOI: 10.15224/978-1-63248-113-9-03
• Views: 0
• Downloads: 0

Abstract: The Software Development and Enhancement Projects (SDANDEP) management is an area of software engineering that is not proving to be particularly highly effective. One of the major effects of this status quo is a waste of considerable sums of money having been invested in projects of this type. While one of the major causes is inability to plan duration and costs of the realization of such projects. On the other hand, this results, among others, from the fact that collecting and use of reliable benchmarking data that would provide possibility to determine dependence between the project’s product size and work effort and its duration in specified realization conditions, is still rare. The goal of this paper is to demonstrate several examples of case studies employing such data, for which these data contributed to the increase in the effectiveness of management of the discussed projects, executed in public administration institutions. The paper also analyzes the source with general benchm

• Publication Date: 16-Dec-2016
• DOI: 10.15224/978-1-63248-113-9-04
• Views: 0
• Downloads: 0