Baharul Islam

Eczema is the most common among all types of skin diseases. A solution for this disease is very crucial for patients to have better treatment. Eczema is usually detected manually by doctors or dermatologists. It is tough to distinguish between different types of Eczema because of the similarities in symptoms. In recent years, several attempts have been taken to automate the detection of skin diseases with much accuracy. Many methods such as Image Processing Techniques, Machine Learning algorithms are getting used to execute segmentation and classification of skin diseases. It is found that among all those skin disease detection systems, particularly detection work on eczema disease is rare. There is also insufficiency in eczema disease dataset. In this paper, we propose a novel deep CNN-based approach for classifying five different classes of Eczema with our collected dataset. Data augmentation is used to transform images for better performance. Regularization techniques such as batch normalization and dropout helped to reduce overfitting. Our proposed model achieved an accuracy of 96.2%, which exceeded the performance of the state of the arts.

The perception of the complex road environment is a critical factor in autonomous driving, which has become the research focus in intelligent vehicles. In this paper, a real-time front vehicle detection system is proposed to ensure safe driving in a complex environment, particularly in congested megacities. This system is based on the YOLO model, which effectively detects and classifies various vehicles from both images and videos. It improves detection accuracy by modifying a feature extraction-based backbone. To the authors’ best knowledge, this is the first time that vehicle detection is implemented on the recently published DhakaAI dataset. Compared to the other available datasets for object detection, such as KITTI, the DhakaAI dataset has a complex environment with numerous vehicles (21 different types). Experimental results demonstrate that the proposed system outperforms the state-of-the-art object detectors. In this method, the mAP (mean average precision) and the FPS (frame per second) is increased by 2.97% and 1.47, 4.64% and 5.57, 4.75% and 3.02, compared to the RetinaNet, SSD, and Faster RCNN on this dataset, respectively.

The increased popularity of stereo photography due to the availability of stereoscopic lens and cameras has aroused research interest in stereo image editing. In this paper, we present an automatic, aesthetic-based warping approach to recompose both the left and right stereo image pair simultaneously using a global optimization algorithm. To maximize image aesthetics, we minimize a set of aesthetics errors formulated based on selected photographic composition rules during the warping process. In addition, our algorithm attempts to preserve the stereoscopic properties by minimizing disparity change and vertical drift in the resulting image. Experimental results shows that our approach successfully relocate salient objects according to the selected photographic rules to enhance compositional aesthetics and maintain disparity consistency to create a comfortable 3D viewing experience.

Mobile Financial Services (MFS) is an approach to offering financial services that combines banking with mobile wireless networks which enables for users to execute banking transaction. It is new term in Bangladesh and getting popularity rapidly. Most people of Bangladesh live in rural areas and almost every family use at least one mobile phone. So, mobile phone is an important device to provide service to them. Almost all banks are trying to provide financial service to maximum people through mobile phone and it's becoming familiar as mobile banking. Already several banks have implemented their mobile banking successfully. In this document, we have described the present condition of mobile banking in Bangladesh and technical architecture of mobile banking. We also showed prospects and limitations of mobile banking in Bangladesh.

Motion is very easy between two points just like for straight line motion. Constant objects need acceleration for speed up at starting point and after reaching highest velocity, it needs to deceleration to stop at end point of the straight line. Suppose there are some turning points of a linear curve, then moving object along the curve will be very jerky at the turning points. This is very unlike how motion happens in the real world and this should be avoided in animations. The objective of this paper is to analysis motion for different kinds of curves that can be formed from same control points and analyze motion characteristics along a path for animation.

Due to the development of Internet and photographic technology the numbers of digital images are increasing rapidly. In this scenario, maintaining the database of images and retrieval of correct image from online database is a challenging task. To perform this task Content Based Image Retrieval (CBIR) is used which is the process of retrieving the most closely matched images automatically by extracting different features. Single feature-based system cannot retrieve image accurately and efficiently. High-dimensional feature reduced the query efficiency and less-dimensional feature reduced query accuracy. So it may be a better solution using multi features for image retrieval. The proposed system is based on CBIR, in which the colour feature extraction is accomplished through constructing a one dimension feature vector. The texture feature extraction is acquired by using gray-level co-occurrence matrix (GLCM) or colour co-occurrence matrix (CCM). The GLCM and CCM are separately combin...

The aspiration to create distinctive belongings and free restriction to one's imagination helps as a powerful impulsion for development of concept art for animation. Concept art is an appearance of illustration where the focal purpose is to express a visual demonstration of a design, thought, or mood for applying in video games, films , animation, or comic books before it is put into the ultimate creation. Concept art is a major element of idea generation, environment creation, background design, retail design, set design, fashion design, and architecture design. Bangladesh is a suitable ground for producing international quality animation products if capacity building can be done. Moreover, previous study found huge possibilities in animation field due to low labor cost. The main objective of this research was to discover the limitations of producing concept art and identify pragmatic solutions to the problems for overall capacity building. We visited most animation studios in ...

Due to the development of Internet and photographic technology the numbers of digital images have been increasing rapidly. In this scenario, maintaining the database of images and retrieval of correct image from online database is a challenging task. To perform this task Content Based Image Retrieval (CBIR) is used which is the process of retrieving the most closely matched images automatically by extracting different features. Single feature-based system cannot retrieve image accurately and efficiently. High dimensional feature reduced the query efficiency and less-dimensional feature reduced query accuracy. So it may be a better solution using multi features for image retrieval. The proposed system is based on CBIR, in which the colour feature extraction is accomplished through constructing a one dimension feature vector. The texture feature extraction is acquired by using gray-level co-occurrence matrix (GLCM) or colour co-occurrence matrix (CCM). The GLCM and CCM are separately ...

Objects cannot occupy the same location in 3D space at the same time. Generally all static objects have no possibility of collision between them. Collision Detection (CD) is to detect collision between objects when they are interpenetrating with each other during animation and physical simulation. In animation, CD is very important topics for research to reduce intersection cost of objects. The objective of this paper is to review all collision detection algorithms and propose a technique for efficient collision detection between complex rigid objects. We used geometry as a bounding volume for each object. It performs the intersection test between the bounding volumes first. If the bounding volumes are not intersecting one another, then the two objects are not intersecting. It can speed up the collision detection. This paper will be helpful for researchers who want to work on collision detection in the field of animation, physical simulation, robotics, and game development.

Ever been a situation where a cyber crime investigation authority is searching for a convicted user who has allegedly done something illegal and the authority only can identify the system where from the crime is committed instead of having any information about the acquitted user exactly they are looking for. If we compare this scenario with our real world offenses that means the police has found the site where the crime is held but they have no idea or clue about the criminal. It should deserve a great concern that this type of thing is happening in our today‟s modern cyber world in each every day. We can easily find any system or network that is doing something offensive and fraud but it is not clear to us how we can find the acquitted user who has used that system to commit that fraud. We‟ve tried to find a solution towards a sound solution of the problem we‟ve been ever facing in our cyber world. In this paper we have proposed a smart input based user authentication method that ...

Page architecture is the primary concept of layout design. It is the basic part of any kind of page design (magazine, newspaper, brochure, book, catalog, etc.) that helps to arrange and approach treatment of essentials (content) on a page. Page layouts supply a simple and visual demonstration of page architecture to the editor, while the macros are more workable and allow playing with complexity in layout design. Detection of page design and innovative visual experience of beauty has become a most important target for contemporary page design. Although there is an established publishing field in Bangladesh but noticed that many of publications house has not skilled designer for page architecture or layout. For this reason the design quality of various publications house lost their aesthetic value. We are studied and analyzed different global publishing firms based on the graphic design to carry out research on the page architecture. The minimalism of this page is formed by the spati...

2013 w w w . a j e r . o r g Page 118 Abstract: -Steganography is a system that hides information in an application cover carrier like image, text, audio, and video. Considerable amount of work has been carried out by different researchers on this subject. Least Significant Bit (LSB) insertion method was more suspicious and low robustness against attacks. The objectives of this study were to analyse various existing system and implement a dynamic substitution based Image Steganography (IS) with a secret key. Our proposed method is more difficult to attack because of message bits are not inserted in to the fixed position. In our method, the message bits are embedded into deeper layer depending on the environment of the host image and a secret key resulting increased robustness. The robustness specially would be increased against those intentional attacks which try to reveal the hidden message.

The pedagogy of teaching and learning has changed with the proliferation of communication technology and it is necessary to develop interactive learning materials for children that may improve their learning, catching, and memorizing capabilities. Perhaps, one of the most important innovations in the age of technology is multimedia and its application. It is imperative to create high quality and realistic learning environment for children. Interactive learning materials can be easier to understand and deal with their first learning. We developed some interactive learning materials in the form of a video for Playgroup using multimedia application tools. This study investigated the impact of students' abilities to acquire new knowledge or skills through interactive learning materials. We visited one kindergartens (Nursery schools), interviewed class teachers about their teaching methods and level of students' ability of recognizing English alphabets, pictures, etc. The course ...

The advancement of cyber technology completely depends on how conveniently we use it. Many people deceived in different ways in our current cyber system. We can prosper ourselves through the utilization of this internet technology. However any country can improve their online security through improving cyber system. On the other hand it may cause precarious outcome if it is incorrectly handled by any unplanned administration. An appropriate mechanism can move forward our cyber world with a safer e-biosphere. The purpose of this paper is to propose an idea that will ensure security and justice in cyber world. This idea proposes to diminish all types of anarchy from the cyber space by ensuring authentic identification to every internet user; securing website browsing; preventing any kind of fraud as well as guarantee truth and justice in the online world.

Desktop publication (DTP) is an unavoidable part of graphic design and it is completely incomplete without typography. There are some rules on typography to apply on innovative design. Most of the designer doesn't follow these rules for their typesetting. That why the aesthetic values of graphics design is going down day-by-day in Bangladesh. It is also more time consumed with complexity. We talked with 50 designers in different design firms and asked some basic questions on typography as questionnaires in different geographical area in Dhaka city. The purpose of this paper is to find the difficulties and solutions to overcome these lacks on typesetting for graphic designer.

The application of computer system has now crossed many different fields. Software has become an essential part of many industrial, military and even commercial systems. We may find programs containing millions of lines of code in both microcomputers and supercomputers. Software reliability is an important research area because of safety critical system. In this paper, a model that can be used for software reliability prediction is explored. The proposed model is implemented using Support Vector Machine (SVM) and has been applied on a custom set of test data. It focused on a particular dataset behavior in predicting reliability. Focusing on a particular dataset behavior is performed to develop an accurate model since the recent work focused on developing a model which can be more accurate. We also build a SVM model to find the relationship between reliability and error rate.

Image Retrieval is the process of retrieving the most closely matched images automatically by extracting the basic features such as edge, shape, color and textures from the query image. The proposed image retrieval system is used texture feature by using grey – level co-occurrence matrix (GLCM) and Color Co – occurrence matrix (CCM). The GLCM and CCM separately combined with a color feature with the use of quantification of HSV color space. The multi-feature extraction is achieved through the Euclidean distance classifier. The proposed system performance is also measured by conducting experiments in different ways.

Gradual transformation from one graphical object or image (source) to another graphical object or image (target) is called morphing. It is useful for creating special effects in animation. This technology is very popular in film and advertisement industries. The idea is distorting the first image into the second one and possible to vice versa. The middle image is a key point of this technology that is neither first image nor second image. If it looks good then probably the entire animated sequence will look good. Complete overview and all of the challenges of this technology is needed to all researchers to work with it. This paper describes an overview and challenges of almost all morphing algorithms that is used in computer animation. Cross-dissolving is one of the problems in morphing technology.

Quality is the essential part software development in the competitive market. Software requirement, design, coding and testing are playing an important role throughout the software development period. Saving at any of the developing stages will greatly reduce the total cost of software development. The key point of this paper is to detect and prevent of defects at earlier stages of software development with the cost control and make trade-off between the quality and the cost. The purpose of this paper is to provide a recommended process to develop software cost estimates for software managers and system engineers. The process is a simplified approach that should be followed by cost estimation professionals. Organization can reach their objectives by adjusting best balance between software quality and cost.

Innovative and creative conceptions are fundamental for advancement of animation technology. Knowledge and intelligence of concept art are very essential to visualize the development of final appearance of animation. These are the essentials for visual demonstration of design, idea, and mood. In the present generation, digital technology is used for visualizing concept art for accomplishing a particular task like animation, video, comic etc. The main task of the concept artist is to have broader understanding and knowledge of principles of art, and communication between thought and visualization. Literature on concept art shows that different authors and researchers paid attentions to and gave emphasis on certain specific elements and ideas. The main objective of this study is to develop a directional model of concept art to fill the information gap in this area. Available literature's will be analyzed and discussed, and finally a directional model will be developed.

ABSTRACT National Payment Switch (NPS) is an approach to offering financial services that combines banking with Automated Teller Machine (ATM), Point of Sale (POS), Mobile Banking (MB) and Internet Banking (IB) which enables for users to execute banking transaction. It is new term in Bangladesh. Most of the people in Bangladesh live in rural areas and the services of banks are being increased through ATM, POS, IB and MB day by day. Almost all banks are trying to provide financial service to maximum customers through these delivery channels and some of them are becoming popular. So a common platform is needed for inter bank transaction through different delivery channels. NPS is such a system for inter-bank transaction in Bangladesh. Already several banks have connected with NPS successfully in Bangladesh. The main purpose of this paper is to provide present condition of NPS, and related services (ATM, POS, MB, IB) in Bangladesh and technical architecture of NPS. We also showed prospects and limitations of NPS in Bangladesh.

The increased popularity of stereo photography due to the availability of stereoscopic lens and cameras has aroused research interest in stereo image editing. In this paper, we present an automatic, aesthetic-based warping approach to recompose both the left and right stereo image pair simultaneously using a global optimization algorithm. To maximize image aesthetics, we minimize a set of aesthetics errors formulated based on selected photographic composition rules during the warping process. In addition, our algorithm attempts to preserve the stereoscopic properties by minimizing disparity change and vertical drift in the resulting image. Experimental results shows that our approach successfully relocate salient objects according to the selected photographic rules to enhance compositional aesthetics and maintain disparity consistency to create a
comfortable 3D viewing experience.