A Convolutional Neural Networks-Based Approach for Texture Directionality Detection

The perceived texture directionality is an important, not fully explored image characteristic. In many applications texture directionality detection is of fundamental importance. Several approaches have been proposed, such as the fast Fourier-based method. We recently proposed a method based on the interpolated grey-level co-occurrence matrix (iGLCM), robust to image blur and noise but slower than the Fourier-based method. Here we test the applicability of convolutional neural networks (CNNs) to texture directionality detection. To obtain the large amount of training data required, we built a training dataset consisting of synthetic textures with known directionality and varying perturbation levels. Subsequently, we defined and tested shallow and deep CNN architectures. We present the test results focusing on the CNN architectures and their robustness with respect to image perturbations. We identify the best performing CNN architecture, and compare it with the iGLCM, the Fourier and the local gradient orientation methods. We find that the accuracy of CNN is lower, yet comparable to the iGLCM, and it outperforms the other two methods. As expected, the CNN method shows the highest computing speed. Finally, we demonstrate the best performing CNN on real-life images. Visual analysis suggests that the learned patterns generalize to real-life image data. Hence, CNNs represent a promising approach for texture directionality detection, warranting further investigation.

Analysis of cassava chip image characterization during drying process

Monitoring method during food processing is an indispensable activity in the industry of food processing. A digital image processing technique is one of the methods to process images into information in the form of product physical condition. This study aimed to monitor the changes in cassava chips image characteristics through the images along the drying process. The image characteristic i.e covered color, texture, and area. The images were captured by using Webcam type Logitech C525 8.0 megapixel autofocus per minute. Then, the result of these images was processed to get color data of R, G, B, H, S, I, L, a*, b* and the texture i.e. energy, homogeneity, contrast, entropy, and to identify chips size was processed by the number of pixels of the image. While the data about the mass changes along the drying process were taken per minute from a digital scale. The results of this study showed that the length of drying made the value of R, G, B, H and I decreased, but the value of S contrastively increased. The area or the number of image pixels declined dramatically in 1 hour of drying, later (after one hour of drying) the decline was almost zero.

Imaging Analysis and Immunophenotype Study of Head Neck and Chest Extramedullary Plasmacytoma

Extramedullar plasmacytoma refers to the primary plasmacytoma (plasmacytoma is a group of diseases, including multiple myeloma, solitary plasmacytoma and extramedullary plasmacytoma), which is a rare soft tissue malignant tumor composed of plasmacytes, accounting for about 4% of all plasmacytomas. The imaging data of 6 cases of extramedullary plasmacytoma confirmed by pathology were analyzed retrospectively. Results among the 6 cases, the mass was located in the oropharynx in 1 case, in the nasal cavity in 2 cases, in the lung in 2 cases, and in the mediastinum in 1 case. CT revealed a soft, clear boundary, multiple density, and contrast scans from medium to medium. MRI showed that the T1 signal was equal or slightly longer, indicating that the T2 signal was equal or slightly longer, and the diffusion of DWI images was clearly limited and the signal separation was low in some lesions. Tumor necrosis was not evident, and enhanced enhancement was observed in contrast enhanced scanning. In other words, there is a specific image characteristic in extramedullary plasmacytoma, but because of its specificity, diagnostic biopsy is necessary for diagnosis. Preoperative CT and MRI examinations can remove lesions, adjacent tissues, and lymph node lesions. This is very important for early diagnosis, treatment and efficacy evaluation of the disease.

Intercultural competence of a specialist in international economics: the parameter of the diplomatic ability

The article highlights some aspects of the problem related to the training of competitive specialists in international economics. The comprehension of the bachelors’ social diplomatic ability (of those who major in Economics) has been proved to be rightful, the designated ability being the main indicator of their resultative professional training (proficiency). The resources of the educational process at a higher educational establishment as a main factor of the specialist’s personality-oriented and professional development, which has a significant image characteristic (that is the diplomatic ability), have been detailed. A productive professional training of a specialist in international economics proved to be opportune, which determines the increased interest of researchers to the resources of the educational process at higher educational establishments where the main stage of becoming a competitive specialist is actualized. In spite of the acquired by researchers theoretical and practical results that might contribute to the deepening of scientific ideas about the constructive ways and means aimed at increasing the efficiency of specialists’ professional training under conditions of modern Ukrainian higher educational establishments, the aspect of students’ professional competency (their diplomatic ability, in particular) in professionally significant situations still remains underestimated. As a result of the done analytical work based on the scientific fund on the designated problem, the issue regarding the markers of the construct «diplomatic ability» has been clarified. The comprehension of the bachelors’ social diplomatic ability has been proved to be rightful, the designated ability being the image characteristic of a competitive specialist in international economics, the indicator of his (her) intercultural competence, the parameter of a resultative professional training at the main stage of acquiring a professional identity during the period of an individual’s university training. Based on the analysis of the best European practices and some creative discoveries that the Ukrainian experience reproduces, the interactive forms of students’ learning-professional activities have been described, which demonstrates the positive dynamics of the training process aimed at the future specialists majoring in international economics. A particular attention is focused on those ones possessing a pedagogical potential in the aspect of developing students’ diplomatic ability, where professional competence and tolerance as a personal property prevail. Keywords: a future specialist in international economics, intercultural competency, diplomatic ability.

CBIR of Batik Images using Micro Structure Descriptor on Android

Batik is part of a culture that has long developed and known by the people of Indonesia and the world. However, the knowledge is only on the name of batik, not at a more detailed level, such as image characteristic and batik motifs. Batik motif is very diverse, different areas have their own motifs and patterns related to local customs and values. Therefore, it is important to introduce knowledge about batik motifs and patterns effectively and efficiently. So, we build CBIR batik using Micro-Structure Descriptor (MSD) method on Android platform. The data used consisted of 300 images with 50 classes with each class consists of six images. Performance test is held in three scenarios, which the data is divided as test data and data train, with the ratio of scenario 1 is 50%: 50%, scenario 2 is 70%, 30%, and scenario 3 is 80%: 20%. The best results are generated by scenario 3 with precision valur 65.67% and recall value 65.80%, which indicates that the use of MSD on the android platform for CBIR batik performs well.

Print-Scan Resilient Binary Map Watermarking Based on DCT and Scrambling

This article describes how combing the characteristics of simple textures and uneven black area distribution of a binary map, a novel blind print-scan resilient watermarking scheme is proposed. First, the flipping probability of each pixel is calculated, and then the image characteristic value matrix is obtained by scrambling and partitioning. Second, a DCT transform is performed on the characteristic value matrix and then the DCT coefficients are modified according to the hidden data. After that, an inverse DCT is made to the modified DCT coefficient matrix, and the pixels of the corresponding block are flipped. Finally, the watermarked map is obtained by inverse scrambling. Experimental results and analysis show that the proposed scheme not only provides a large capacity and good imperceptibility, but also can resist the impact of a print-scan operation, and has strong robustness. Meanwhile, compared with the existing algorithms, it has a low implementation complexity and can be applied to military maps, engineering design drawings and other binary images.