Comparative analysis of tineye and google reverse image search engines Meenakshi Kondal Faculty of computer science, Goswami ganesh dutta sanatan dharma college, Chandigarh, Affiliation punjab university, India. meenakshikondal3@gmail.com Abstract- Daily on the web, huge amount of photos are there and it is difficult for us to locate authorized image. To find out the origin of a picture, an image search engine, which is an excellent tool, helps us. Searching can be based on similar pictures, keywords or links to an image which help to find deliberate images from different pictures warehouse. Image retrieval is the technique of retrieving, looking, and browsing the pictures from a data ware house. Search engines allow us to understand pick images and the background in which they are placed. At the same time, it is difficult for search engines to transliterate user’s search results by keywords and this deve lops into ambiguous which is removed from acceptable. So it is necessary to use a primary-based fulfilled search to clear up the inconsistency in image retrieval. This is very helpful and an excellent utensil for those who are in digital marketing to see, if any using photo changes without permission. If there’s any copyright violation, we can address the matter. This paper discusses the idea and function ing of image search engines. From well-liked search engines, we have chosen images for presentation and diagnosis of the results. In this paper, two image search engines tineye and google reverse image search, officially called google search, were evaluated on the basis of their search capabilities and response time; Google chrome was used as the web browser for the study. Keywords- Reverse image search, Transliterate, Image retrieval. Introduction Search engines, as it go on to browse, find index and store information on specific image. The main motive of image search engines is to upload or paste an image in the URL and it searches for it to find that same image across the web. Searching goes thought textual description of the image given by user or content associated with a selected sample image. Sometimes it finds assigned images and results as a bunch of images. Now at this situation various dimensions measures such as quality of an image, color, discover, manipulated versions, shape, trimmed and edited parts are used for comparing the images. The first image identification technology was used by Tineye, to operate if a picture was changed, modified, or resized from its original state [2]. It quickly finds copyright violations and detects image fraud. We cannot upload bulk images; it could slow down the system choosing one at a time. The negative thing about the search results is that the images can have little in common with the original. Tineye found images used with other images of the exact same composition of the selected image and it provided the same approach for many years. In my opinion, they have motorized up their corresponding algorithm [4]. Google search engines do its best to identify what is the subject of an image. Searching splits between three sections: what the algorithm thinks is in the photo; visually similar images results, and pages that include identical images. For many decades, Google search for image information was done by using query keyword. Google uses algorithms for attributes like form, size, and color to induce similar footage in images [4]. Google uses this to match input images to alternative images within the Google images index and additional image collections [5]. Objective of the study 1. To look over the productivity of image search engines. 2. To observe the applicability of the results for the input images.