Semantic image segmentation is a fundamental yet challenging problem, which can be viewed as an extension of the conventional object detection with close relation to image segmentation and classification. It aims to partition images into non-overlapping regions that are assigned predefined semantic labels. Most of the existing approaches utilize and integrate low-level local features and high-level contextual cues, which are fed into an inference framework such as, the conditional random field (CRF). However, the lack of meaning in the primitives (i.e., pixels or superpixels) and the cues provides low discriminatory capabilities, since they are rarely object-consistent. Moreover, blind combinations of heterogeneous features and contextual cues exploitation through limited neighborhood relations in the CRFs tend to degrade the labeling performance. This paper proposes an ontology-based semantic image segmentation (OBSIS) approach that jointly models image segmentation and object detection. In particular, a Dirichlet process mixture model transforms the low-level visual space into an intermediate semantic space, which drastically reduces the feature dimensionality. These features are then individually weighed and independently learned within the context, using multiple CRFs. The segmentation of images into object parts is hence reduced to a classification task, where object inference is passed to an ontology model. This model resembles the way by which humans understand the images through the combination of different cues, context models, and rule-based learning of the ontologies. Experimental evaluations using the MSRC-21 and PASCAL VOC'2010 data sets show promising results.

In RBIR, texture features are crucial in determining the class a region belongs to since they can overcome the limitations of color and shape features. Two robust approaches to model texture features are Gabor and curvelet features. Although both features are close to human visual perception, sufficient information needs to be extracted from their sub-bands for effective texture classification. Moreover, shape irregularity can be a problem since Gabor and curvelet transforms can only be applied on the regular shapes. In this paper, we propose an approach that uses both the Gabor wavelet and the curvelet transforms on the transferred regular shapes of the image regions. We also apply a fitting method to encode the sub-bands’ information in the polynomial coefficients to create a texture feature vector with the maximum power of discrimination. Experiments on texture classification task with ImageCLEF and Outex databases demonstrate the effectiveness of the proposed approach.

Providing easy access to Picture Archiving and Communications Systems (PACS) of selected image slices based on its diagnosis would be useful to teach medical students and educators and for government policies. This requires a simplified retrieval presenting only the key images to the doctors that has the diagnosis for every study of interest, thus saving doctors time. An automatic detection of diagnosis will help the radiographers in saving time since they consume a lot of time in the process of detecting skull fractures manually and with the automatic annotation of the pathological terms only to the key slices that has findings/diagnosis of the entire image set an efficient retrieval of specific key slices can be achieved. One important abnormality in the skull is its fracture. The proposed research goal concentrates on the automatic detection of normal and abnormal skull images as a part of our work. This paper presents a simple and fast automatic method to detect skull fracture in Digital Imaging and Communications in Medicine (DICOM) to extract the skull bone using histogram based thresholding and with the neighboring pixel connectivity search to identify the fracture. The experimental results of this approach are reliable with high detection rate.

Multimedia content has been growing quickly and video retrieval is regarded as one of the most famous issues in multimedia research. In order to retrieve a desirable video, users express their needs in terms of queries. Queries can be on object, motion, texture, color, audio, etc. Low-level representations of video are different from the higher level concepts which a user associates with video. Therefore, query based on semantics is more realistic and tangible for end user. Comprehending the semantics of query has opened a new insight in video retrieval and bridging the semantic gap. However, the problem is that the video needs to be manually annotated in order to support queries expressed in terms of semantic concepts. Annotating semantic concepts which appear in video shots is a challenging and time-consuming task. Moreover, it is not possible to provide annotation for every concept in the real world. In this study, an integrated semantic-based approach for similarity computation is proposed with respect to enhance the retrieval effectiveness in concept-based video retrieval. The proposed method is based on the integration of knowledge-based and corpus-based semantic word similarity measures in order to retrieve video shots for concepts whose annotations are not available for the system. The TRECVID 2005 dataset is used for evaluation purpose, and the results of applying proposed method are then compared against the individual knowledge-based and corpus-based semantic word similarity measures which were utilized in previous studies in the same domain. The superiority of integrated similarity method is shown and evaluated in terms of Mean Average Precision (MAP).

Similarity between two sentences can be determined by either comparing their commonalities or their differences. Commonalities, which reflect similarity judgment, connect the two sentences while differences, which reflect dissimilarity judgment, represent the unique way of self-identification. Although both of them are essential in determining sentence similarity, however, the existing methods only focus on single perspective, mostly the perspective of commonalities. This paper presents a method which calculates the sentence similarity from multiple perspectives by taking both the commonalities and differences into consideration. The experimental result on a standard data set shows that the proposed method outperforms the baseline, which is the existing most outstanding single perspective measure, with statistically significant improvement.

Artificial Immune Recognition System (AIRS) is an immune inspired classifier that competes with famous classifiers. One of the most important components of AIRS is resource competition. The goal of resource competition is the development of the fittest individuals. Resource competition phase removes weakest individuals and selects strongest (seemly good) individuals. This type of selection has high selective pressure with a loss of diversity. It may generate premature memory cells and decrease the accuracy of classifier. In this study, the Real World Tournament Selection (RWTS) method is incorporated in resource competition phase of AIRS to prevent this issue and experiments are conducted to evaluate the accuracy of new algorithm (RWTSAIRS). The combination of cross validation and t test is used as evaluation method. Algorithms tested on benchmark datasets of the UCI machine learning repository show that RWTSAIRS obtained higher accuracy than AIRS in all cases and that the difference between accuracies of two algorithms was significant in majority of cases.