Scene Text Detection and Segmentation based on Cascaded Convolution Neural Networks - 2017


Scene text detection and segmentation are 2 important and difficult research problems in the sphere of pc vision. This paper proposes a novel methodology for scene text detection and segmentation primarily based on cascaded convolution neural networks (CNNs). In this method, a CNN-primarily based text-aware candidate text region (CTR) extraction model (named detection network, DNet) is designed and trained using each the edges and the entire regions of text, with that coarse CTRs are detected. A CNN-based CTR refinement model (named segmentation network, SNet) is then created to exactly phase the coarse CTRs into text to induce the refined CTRs. With DNet and SNet, a lot of fewer CTRs are extracted than with traditional approaches whereas additional true text regions are kept. The refined CTRs are finally classified using a CNN-based CTR classification model (named classification network, CNet) to urge the ultimate text regions. All of these CNN-primarily based models are modified from VGGNet-16. In depth experiments on three benchmark data sets demonstrate that the proposed technique achieves the state-of-the-art performance and greatly outperforms alternative scene text detection and segmentation approaches.

Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here

PROJECT TITLE :Image Haze Removal via Reference Retrieval and Scene Prior - 2018ABSTRACT:Photography of hazy scene usually suffers from low-contrast which degrades the visibility of the scene. The performance of single-image
PROJECT TITLE :Strokelets: A Learned Multi-Scale Mid-Level Representation for Scene Text RecognitionABSTRACT:In this paper, we have a tendency to are involved with the matter of automatic scene text recognition, which involves
PROJECT TITLE :Text-Attentional Convolutional Neural Network for Scene Text DetectionABSTRACT:Recent deep learning models have demonstrated strong capabilities for classifying text and non-text parts in natural images. They extract
PROJECT TITLE :Scene size limits for polar format algorithmABSTRACT:Synthetic aperture radar (SAR) is a type of remote sensing where coherent radar echoes transmitted from a moving platform are processed to create a picture of
PROJECT TITLE :Human-Machine CRFs for Identifying Bottlenecks in Scene UnderstandingABSTRACT:Recent trends in image understanding have pushed for scene understanding models that jointly reason regarding varied tasks such as object

Ready to Complete Your Academic MTech Project Work In Affordable Price ?

Project Enquiry