International Journal of Computer (IJC - Global Society of Scientific Research and Researchers, GSSRR)
Not a member yet
459 research outputs found
Sort by
Scene Classification using Localized Histogram of Oriented Gradients Method
Get PDFScene classification is an important and elementary problem in image understanding. It deals with large number of scenes in order to discover the common structure shared by all the scenes in a class. It is used in medical science (X-Ray, ECG and Endoscopy etc), criminal detection, gender classification, skin classification, facial image classification, generating weather information from satellite image; identify vegetation types, anthropogenic structures, mineral resources, or transient changes in any of these properties. In this paper, at first we propose a feature extraction method named LHOG or Localized HOG. We consider that an image contains some important region which helps to find similarity with same class of images. We generate local information from an image via our proposed LHOG method. Then by combing all the local information we generate the global descriptor using Bag of Feature (BoF) method which is finally used to represent and classify an image accurately and efficiently. In classification purpose, we use Support Vector Machine (SVM) that analyze data and recognize patterns. The basic SVM takes a set of input data and predicts, for each given input, which of two possible classes forms the output. In our paper, we use six different classes of images
The Unified Methodology for Application and Database Development UMADD (Using “abbCode” Framework)
Get PDFThe study describes a new methodology for architecting software using a new developed tool in a way that make development processes easier, increase productivity and reducing bugs and potential errors avoiding overheads.
Aggregating News Articles – NewsInn Algorithm
Get PDFNewsInn is an algorithm designed to aggregate articles from multiple news sources into one general, story-based meta-article. This entity is then displayed by calculating the most relevant news article in relation to it, and by listing underneath it the remainder of articles. Using a simple User Interface, the algorithm makes it easy for end users to understand current events, the coverage that they have and the impact that the story carries.Using multiple Natural Language Processing techniques, Newsinn manages to parse 19 different news source and aggregate more than 700 articles daily into their respective meta-articles. Seeing how even a human would have issues deciding if certain articles are related or not, as it depends on what criteria is used for making this decision, NewsInn uses different parameters to control the level of aggregation.
Mouse Jacking: A Survey
Get PDFIn the modern era of technology, devices have become smaller, more user friendly and most importantly, wireless. Gadgets these days come with convenient wireless variants for the user. These wireless gadgets allow the user to access the host machine from a distance that varies depending upon the range of the radio signal. The latest innovation of wireless mouse has given the user freedom from the old technology of wired mouse. However, there is a serious threat that comes along with the facility of a wireless mouse. The data transmitted from the click on the mouse to the radio transceiver attached to the computer is not in an encrypted format, and is usually considered as data that is not confidential or important. Mouse Jacking is a set of vulnerabilities that is associated with wireless, non-Bluetooth mice and keyboards. Mouse Jacking allows the hacker or unauthorized user to access the target computer from 100 meters away by using an inexpensive USB dongle
Satellite Image Classification Using Moment and SVD Method
Get PDFThe motivation we address in this paper is to classify satellite image using the moment and singular value decomposition (SVD) method; both proposed methods are consisted of two phases; the enrollment and classification. The enrollment phase aims to extract the image classes to be stored in dataset as a training data. Since the SVD method is supervised method, it cannot enroll the intended dataset, instead, the moment based K-means was used to build the dataset. Thereby, the enrollment phase began with partitioning the image into uniform sized blocks, and estimating the moment for each image block. The moment is the feature by which the image blocks were grouped. Then, K-means is used to cluster the image blocks and determining the number of cluster and centroid of each cluster. The image block corresponding to these centroids were stored in the dataset to be used in the classification phase. The results of enrollment phase showed that the image contains five distinct classes, they are; water, vegetation, residential without vegetation, residential with vegetation, and open land. The classification phase consisted of multi stages; image composition, image transform, image partitioning, feature extraction, and then image classification. The SVD classification method used the dataset to estimate the classification feature SVD and compute the similarity measure for each block in the image, while the moment classification method used the dataset to compute the mean of each column and compute the similarity measure for each pixel in the image. The results assessment was carried out on the two classification paths by comparing the results with a reference classified image achieved by Iraqi Geological Surveying Corporation (GSC). The comparison process is done pixel by pixel for whole the considered image and computing some evaluation measurements. It was found that the classification method was high quality performed and the results showed acceptable classification scores. In the SVD method, the score was about 70.64%, and it is possible to rise up to 81.833% when assuming both classes: residential without vegetation and residential with vegetation are one class.Whereas, the classification score was about 95.84% when using the moment method. This encourage results indicates the ability of proposed methods to efficient classifying multibands satellite image.
Complementary Graph Coloring
Get PDFThe objective of the Graph Coloring problem is to color vertices of a graph in such a way that no two vertices that share an edge are assigned the same color. Aircraft Scheduling, Frequency Assignment, register allocation are all real life applications that can be solved using graph coloring. Graph Coloring is a well-known NP-complete problem to the academia in computer science and mathematics. In this paper we use the concept of complementary graphs to come up with a new heuristic for graph coloring. Our results are compared with an exact algorithm and other heuristic algorithms to evaluate our algorithm’s performance.
Infrastructure-less Vehicular Communication System Using Li-Fi Technology
Get PDFThis paper introduces vehicle to vehicle (v2v) communication system using Li-Fi technology. The lightning quick transfer of information between vehicles becomes mandatory when danger is imminent as it can instantly diffuse a potentially hazardous situation. Connected cars will help cities and states cut down on congestion and improve safety. On the road, cars will communicate with each other, automatically transmitting data such as speed, position, and direction, and send alerts to each other if a crash seems imminent. We consider the several scenarios: 1) communication between car and RSU 2) inter vehicular communication 3) communication based network system. The reach ability, delay in transmission and percentage collisions are evaluated with respect to the average distance between cars using pixel oriented visualization. With the help of LEDs fitted in the car, we can transmit data seamlessly using rapid pulse of light over VANET (Vehicular Ad-hoc network) for high speed communications
Proxy Signcrypion Scheme Based on Hyper Elliptic Curves
Get PDFDelegation of rights is promising in Internet applications like distributed computing, e-cash systems, global distribution networks, grid computing, mobile agent applications, and mobile communications. This paper presents a novel Proxy Signcrypion Scheme based on hyper elliptic curves, attractive for resource constrained environment due to its shorter key size. It has properties of warrant integrity, message integrity, message confidentiality, warrant unforgeability, message unforgeability, proxy non repudiation and public verifiability. The proposed scheme has reduced computational cost as compared to the other existing schemes
In the Cloud Storage Market How Users are Using it without Hesitation (Report 2016)
Get PDFCloud Storage, today has become an integral part of IT related persons lives. It also use in many businesses institute to store their important data. But, they always concern about its security. User of Cloud Storage can’t use it without hesitation. So, it is important to know for provider and builder that why user feel unsecure and what are the factors for hesitation to use Cloud Storage. In this paper we focus on user opinion for their hesitation to use Cloud Storage.
Designing an Arabic Handwritten Segmentation System
Get PDFThe greatest difficulty facing the recognition of Arabic handwritten words is segmentation, because Arabic handwriting is cursive with complex multi-form styles. Hence, intensive research efforts are needed to reach an effective Arabic handwriting segmentation system. This paper presents a system which uses morphological features of the Arabic characters for segmentation. The proposed system segments non-overlapped (horizontally connected -e.g. "???") as well as overlapped (vertically connected - e.g. "???") characters. The result is not very good one. However, it arrives at good directives for more research. As the writing was freely without any restrictions, both over-segmentation and under-segmentation problems affect the system.