Sketch Based Image Retrieval
نویسندگان
چکیده
Sketch based image retrieval is a task that has been explored a lot recently as an alternative method for image retrieval. We develop this task on The Sketchy Database, where we use Siamese and Triplet network to perform sketch based image retrieval. We employ deep residual learning network as the constituent network in the Siamese and Triplet architecture and use new data augmentation techniques for the task. Recent success of deep residual network (ResNet) suggests that it performs better than the previous architectures.
منابع مشابه
Enhancing Traditional Keyword-Based Image Search Through Sketch-Based Image Retrieval
This paper Sketch-based image retrieval (SBIR) has become one of the most active research areas in the past few years. A sketch-based image retrieval approach by using combined use of query by sketch, re-ranking and relevance feedback as techniques is proposed to ease user interaction and improve retrieval. One of the main challenges in sketch-based image retrieval (SBIR) is to measure the simi...
متن کاملSketch Based Image Retrieval by Using Feature Extraction Technique
Nowadays, touch screen technology makes drawing a sketch easier. It also makes searching and surfing easier for disabled children. Retrieving images with a sketch is a highly desired feature for disabled children with autism. The image retrieval system was defined as a computer system for searching, browsing and accessing the image. It is not easy for autistic children to recognize suitable key...
متن کاملAn Improved Histogram of Edge Local Orientations for Sketch-Based Image Retrieval
Content-based image retrieval requires a natural image (e.g, a photo) as query, but the absence of such a query image is usually the reason for a search. An easy way to express the user query is using a line-based hand-drawing, a sketch, leading to the sketch-based image retrieval. Few authors have addressed image retrieval based on a sketch as query, and the current approaches still keep low p...
متن کاملContent-Based Image Retrieval over the Web Using Query by Sketch and Relevance Feedback
This paper investigates the combined use of query by sketch and relevance feedback as techniques to ease user interaction and improve retrieval effectiveness in content-based image retrieval over the World Wide Web. To substantiate our ideas we implemented DrawSearch, a prototype image retrieval by content system that uses color, shape and texture to index and retrieve images. The system avails...
متن کاملDeep Multi-task Attribute-driven Ranking for Fine-grained Sketch-based Image Retrieval
With touch-screen devices becoming ever more ubiquitous, sketch holds great promise as an intuitive and efficient mode of input compared to classic alternatives. This has motivated a major revival of interest in vision-based analysis of sketches, notably in sketch-based image retrieval (SBIR). Superior to classic SBIR methods, finegrained SBIR (FG-SBIR) methods [1] are proposed to make fine-gra...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2016