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, .Net) 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, .Net) is then created to exactly phase the coarse CTRs into text to induce the refined CTRs. With .Net and .Net, 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, .Net) 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 : Tensor Canonical Correlation Analysis Networks for Multi-view Remote Sensing Scene Recognition ABSTRACT: It has been demonstrated that using a convolutional neural network, also known as CNN, is an efficient method
PROJECT TITLE : Bioinspired Scene Classification by Deep Active Learning With Remote Sensing Applications ABSTRACT: Scene parsing, robot motion planning, and autonomous driving are all examples of applications that require
PROJECT TITLE : A Multiple-Instance Densely-Connected ConvNet for Aerial Scene Classification ABSTRACT: Aerial views, in contrast to natural scenes, generally consist of many items that are crowded on the surface from a bird's
PROJECT TITLE : Dynamic Scene Deblurring by Depth Guided Model ABSTRACT: Object movement, depth fluctuation, and camera shake are the most common causes of dynamic scene blur. For the most part, present approaches use picture
PROJECT TITLE : MSFD Multi-Scale Segmentation-Based Feature Detection for Wide-Baseline Scene Reconstruction ABSTRACT: Conventional detectors, such as SIFT, SURF, FAST, A-KAZE, and MSER, have a difficulty with sparse and non-uniform

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

Project Enquiry