Abstract
Sketch based image retrieval (SBIR) is a sub-domain of Content Based Image Retrieval(CBIR) where the user provides a drawing as an input to obtain i.e retrieve images relevant to the drawing given. The main challenge in SBIR is the subjectivity of the drawings drawn by the user as it entirely relies on the user's ability to express information in hand-drawn form. Since many of the SBIR models created aim at using singular input sketch and retrieving photos based on the given single sketch input, our project aims to enable detection and extraction of multiple sketches given together as a single input sketch image. The features are extracted from individual sketches obtained using deep learning architectures such as VGG16 , and classified to its type based on supervised machine learning using Support Vector Machines. Based on the class obtained, photos are retrieved from the database using an opencv library, CVLib , which finds the objects present in a photo image. From the number of components obtained in each photo, a ranking function is performed to rank the retrieved photos, which are then displayed to the user starting from the highest order of ranking up to the least. The system consisting of VGG16 and SVM provides 89% accuracy.
Highlights
Content based image retrieval is a sub-domain under information retrieval
From Table - II, it is inferred that a pure deep learning based approach proves to be inefficient due to the less features contained in the sketches
Table - III shows that the machine learning based approach using Support Vector Machine (SVM) works better with deep learning based feature extraction
Summary
To obtain information about something, it is required to be able to express it unambiguously and with relevance. Pictographs and sketches are one of the few ways to describe one's need for relevant information. With the advent of technology, many aim to gain knowledge through information remotely, by using search engines. This explicit description about the object is used in search engines to get relevant results in the form of images, websites, videos etc. Information retrieval is a domain of interest to many problem solvers where the main difficulty lies in the ability to bridge the gap between information available and the query given by the user. Content based image retrieval is a sub-domain under information retrieval
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call