The methodology is implemented in five phases which are review paper, collecting data, compare data, find out strength and weaknesses and come out with innovative ideas. Therefore, this study was conducted to study the techniques that have been used previously for defined the suitable technique that can be used and help in images features extraction because features extraction is the most important part in NDID research, in order to allow the system to understand what requirements and unique structure for different images. The issue and problem in NDID related to detection and clustering the similar images. Various techniques are used to help manage, detect and clustering ND images contained in the database, but the problem is, how accurately detecting NDID in features extraction and this study are still ongoing and facing several issue and problems. The content inside the database is in high quantities. Research in NDID always related with the database either conventional or cloud computing. Near-duplicate images detection (NDID) is a different image but have similarity in scenery, object and content. The detected near duplicate images help the users to avoid redundancy in images, detect copyright infringement, illegal copy of images detection, facilitates users' browsing since image search engine returns multiple copies of image for a particular query. This results in effective detection of near duplicate images. In view of the relationship between the inquiry image and the images in the image set, the near duplicate images are recognized. Once the features are extracted, similarity measure is calculated. Initially features are extracted from the images using Pulse-Coupled Neural Network. In this work, a detection methodology is presented to identify near duplicate image from the image set for an inquiry image by the user. Discovery of these near duplicate images may permit the users to abstain from encountering the presentation of a similar picture in the result set. These similar / transformed images are available in the internet and they are displayed as a result of user search. Near duplicate images are nothing but the similar images with minute change in the original image. The experimental results show that our PCNN-NDD system enhances the detection results and improves the accuracy when compared to other traditional systems. The advantage of the proposed work lies in the proper setting of PCNN parameters to identify the similar images. Our system is capable of improving the accuracy effectively. The proposed work Pulse Coupled Neural Network based Near Duplicate Detection of Images (PCNN-NDD) is a two-step process-(1) feature extraction using PCNN and (2) fast image similarity measurement using correlation coefficient. In this paper, PCNN is applied in the detection of near duplicate (ND) images. Pulse Coupled Neural Network (PCNN) is found to be a suitable processor for all the image processing techniques including feature extraction. The existing works in ND detection are less accurate in the identification of similar images as near duplicates. The illegal copies of images are identified to protect copyright enforcement and reduce redundancy. This review provides research directions to the fellow researchers who are interested to work in this field.ฤก Abstract-Near Duplicate images are variants of original image with some transformations / manipulations / forgeries in it. We also discuss the main challenges in this field and how other researchers addressed those challenges. In this paper, we review the state-of-the-art computer vision based approaches and feature extraction methods for the detection of near duplicate images. There is no proper survey in literature related to near duplicate detection of images. There are several tasks in image understanding such as feature extraction, object detection, object recognition, image cleaning, image transformation, etc. The main application of computer vision is image understanding. Computer vision is concerned with the automatic extraction, analysis and understanding of useful information from digital images. The presence of near-duplicates affects the performance of the search engines critically. For example, after images are posted on the internet, other web users can modify them and then repost their versions, thereby generating near-duplicate images. Nowadays, digital content is widespread and simply redistributable, either lawfully or unlawfully.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |