International Journal of Computer Techniques

1-5

Authors: - IJCTVikram Dwivedi ,Dr. Paresh Rawat

The underwater image segmentation is a challenging field of research due to poor illumination condition. Therefore this paper reviews the various issues and problems based on the existing researches in underwater segmentation field. Since underwater images have many uses in general purposes like in marine engineering, analysis and monitoring of underwater animals and plants and for monitoring of oil wells. Thus, underwater segmentation problem can be considered as fuzzy problem. Therefore this paper reviews the fuzzy clustering algorithm for image segmentation. Fuzzy C-Means clustering based underwater image segmentation methods separates the underwater objects using clustering and thresholding. It is found that fuzzy based approaches are not such efficient in underwater environment and thus not much explored. The efficiency of the fuzzy based methods various with different images and objects. Paper pointed out various challenges after reviewing the previous work. It is require improving the efficiency of the fuzzy based systems for segmenting the underwater images.

6-12

Authors: - IJCTMs. Akila .S, Ms. Siva sankari A.

Solid waste management is a big challenge in urban areas for most of the countries throughout the world. There are many technologies are used for waste collection as well as for well managed recycling. The concurrent effects of a fast national growth rate, of a large and dense residential area and a pressing demand for urban environmental protection create a challenging framework for waste management.In this project humans and vehicles were used to do that work and here we are using automatic technique to detect garbage level in Garbage Can. For that, ID number is given to each can. Also as soon as the Garbage Can is full / over flowing then a Message is sent to the server from where all the garbage collection vehicles are allotted.The main urban wastages are household food waste, agricultural waste, human and animal waste. The waste component of landfill is broken down by microorganisms to form a liquid ‘leachate’ which contains bacteria, rotting matter and maybe chemical contaminants from the landfill.

20-28

Authors: - IJCTMs. Sangeetha .R, Mrs. Sangeetha Lakshmi G.

A location-aware news feed (LANF) system generates news feeds for a mobile user based on her spatial preference her current location and future locations) and non-spatial preference (i.e., her interest). Existing LANF systems simply send the most relevant geo-tagged messages to their users. Unfortunately, the major limitation of such an existing approach is that, a news feed may contain messages related to the same location (i.e., point-of-interest) or the same category of locations (e.g., food, entertainment or sport). We argue that diversity is a very important feature for location-aware news feeds because it helps users discover new places and activities. In this paper, we propose DMobiFeed; a new LANF system enables a user to specify the minimum number of message categories (h) for the messages in a news feed. In D-MobiFeed, our objective is to efficiently schedule news feeds for a mobile user at her current and predicted locations, such that (i) each news feed contains messages belonging to at least h different categories, and (ii) their total relevance to the user is maximized. To achieve this objective, we formulate the problem into two parts, namely, a decision problem and an optimization problem. For the decision problem, we provide an exact solution by modeling it as a maximum flow problem and proving its correctness. The optimization problem is solved by our proposed three-stage heuristic algorithm.

33-36

Authors: - IJCTNisha Kumari Dogra , Maninder Kaur

Image enhancement is a mean as the improvement of an image appearance by increasing dominance of some features or by decreasing ambiguity between different regions of the image. Many images such as medical images, remote sensing images, electron microscopy images and even real life photographic pictures, suffer from poor contrast. Therefore there are many techniques of image enhancement in image processing such as Fast Ostu’s method, Histogram equalization (HE) method, Particle swarm optimization (PSO) , Honey Bee (HB) In this paper, a new approach to automatic image enhancement using HB is implemented by specifying intensity of the edges pixels and also earlier reported PSO results were used. Further comparatively analysis is performed between HB and PSO results. The obtained results indicate that the proposed HB yields better results in the terms of both the maximization of number of the pixels in the edges and peak signal to noise ratio (PSNR). Computational time is also relatively small in the HB as compared to the PSO

37-43

Authors: - IJCTSamruddhi Yadav, Prof.Swati Deshpande , Prof.Smita Bansod

Steganography is a process that involves hiding a secret message in an appropriate carrier like image, audio, video or text in such a way that secret message does not attract attention to itself and remains invisible. Cryptography is an art of protecting information by transforming it into an unreadable format called Cipher text only those possessing a secret key can decipher the message into plain text. A combined approach using Image Steganography and Privatekey Cryptography has been proposed, the cover image is transformed using Integer Wavelet Transform (IWT) and plain text (secret message) is encrypted using Advanced Encrypted Standards (AES). The Encrypted text is then embedded into cover image using proposed assignment algorithm. This system will offer higher security and robustness against image processing attacks and low-pass filtering attacks compared to older system with good embedding capacity, also the stego image and the secret message will have good visual quality. The system will have improved results in terms of PSNR and MSE values.

52-56

Authors: - IJCTShashank Dubey ,Vidya Chitre

Cloud computing is a powerful technology that are highly used to perform large- scale and complex computing. It completely remove requirement to maintain expensive computing hardware, or software and large space. Massive growth has been observed in the generation of data or big data over the year through cloud computing. For processing and anlaysing result from that large data generally require lots of computational power and large infrastructure requirement. Hence there is a need to conjoined big data with cloud computing. Since this big data is important to analysis in order to extract insight knowledge from the data. Traditional association rule mining for frequent itemset which scan the dataset into main memory may become inconvenient when handling large dataset. Hence there is need of processing this dataset on multiple commodity machine using parallel technique of Map Reduce Framework. This paper gives overview of different big data mining algorithm used for processing dataset.