NDLI: Scene Text Analysis using Deep Belief Networks

Please wait, while we are loading the content...

A GPU based Real-Time CUDA implementation for obtaining Visual Saliency

Fingerprint Enhancement Using Unsupervised Hierarchical Feature Learning

A Schrödinger formalism for simultaneously computing the Euclidean distance transform and its gradient density

Duplication Detection for Image Sharing Systems

Finding group interactions in social gathering videos

Particle Coding for Meshfree Cutting of Deformable Assets

Total Cluster: A person agnostic clustering method for broadcast videos

Anatomical Model-Guided Segmentation of Brain MR Image Sequences

Multispectral Multifocus Image Fusion with Guided Steerable Frequency and Improved Saliency

Generalized Synthesis and Analysis Prior Algorithms with Application to Impulse Denoising

Statistical Learning for Texture Characterization

Discovery of Sparse Contextual Relationships for Activity Recognition in Continuous Videos

Knowledge Sharing and Cooperation Based Adaptive Boosting for Robust Eye Detection

Multiscale Intuitionistic Fuzzy Roughness Measure for Color Image Segmentation

A new energy minimization framework and sparse linear system for path planning and shape from shading

Parametric Dictionaries and Feature Augmentation for Continuous Domain Adaptation

Localization of Curved Scene Text in Video based on Fuzzy Curve Tracing of Extracted Planar Surface

Distributed Video Coding using Local Rank Transform

An Interactive Framework for Reconstructing 3D Neuronal Structures

Facet-JFA: Faster computation of discrete Voronoi diagrams

A new SIFT matching criteria in a genetic algorithm framework for registering multisensory satellite imagery

Crowd Abnormality Detection and Localization: A Matrix Decomposition Approach

3D Action Recognition by Learning Sequences of Poses

Ensemble of Statistically Independent Filters for Robust Contact Lens Detection in Iris Images

Monocular Motion Segmentation Of Rigid Bodies Using In-Frame Shear Constraints

Multi-epipolar plane image based 3D reconstruction using robust surface fitting

Disparity based compression technique for focused plenoptic images

Removing Structural Noise in Handwriting Images using Deep Learning

Robust Tracking of Objects through Turbulence

ProLoSAC: An Improved RANSAC Algorithm for Pairwise Registration of 3D Point Clouds

Writer Identification using a Deep Neural Network

One-Time Biometric Token based Authentication

Compression of Noisy Depth Image using Planes

Morphology based Classification of Leukemia Cell lines: K562 and MOLT in a Microfluidics based Imaging Flow Cytometer

Extraction of True Palm-dorsa Veins for Human Authentication

Application of Forgery Localization in Overlay Text Detection

A Novel Approach for Computer Aided Diagnosis of Schizophrenia using Auditory Oddball Functional MRI

Simulation and Rendering of Pitting Corrosion

Temporal Stationarity Based Prediction Method For Lossless Video Coding

Saliency Detection based on a Sparsity of Segments Model

A Flow-based Interest Point Detector for Action Recognition in Videos

A novel graph matching based approach for land-cover classification of multi-temporal images

Techniques for Improving the Performance of Image Retrieval using Relevance Feedback

Concept Level Discriminant Analysis Techniques for Dimension Reduction in Image Classification Tasks

A Robust Oversegmentation Algorithm using Colour and Geometric Cues

Face Recognition using Entropy based Face Segregation as a Pre-processing Technique and Conservative BPSO based Feature Selection

3D Visual Speech Animation from Image Sequences

Color Image Retrieval Using Color Histogram and Orthogonal Combination of Linear Binary Pattern

A Novel Non-rigid Free-form Deformation for Consistent Registration of Digital Elevation Models

Face Recognition in Surveillance Conditions with Bag-of-words, using Unsupervised Domain Adaptation

Digitization of Historic Inscription Images using Cumulants based Simultaneous Blind Source Extraction

Blind 3D Video Watermarking Based on 3D-HEVC Encoder Using Depth

Top Down Approach to Detect Multiple Planes from Pair of Images

A Sketch-Based Approach To Video Retrieval Using Qualitative Features

Multi-criteria Energy Minimization with Boundedness, Edge-density and Rarity, for Object Saliency in Natural Images

Semantic Motion Segmentation Using Dense CRF Formulation

Revealing What to Extract from Where, for Object-Centric Content Based Image Retrieval (CBIR)

Super-resolving a Single Intensity/Range Image via Non-local Means and Sparse Representation

Enhancing Shape from Focus-Measure-Fusion and Sparse Representation

Vision Based Human Pose Estimation for Virtual Cloth Fitting

Guess from Far, Recognize when Near: Searching the Floor for Small Objects

Better Guiding the Guided Range Image Filter for Range-Image Super-resolution

Commercial Block Detection in Broadcast News Videos

Human Trajectory Forecasting In Indoor Environments Using Geometric Context

Domain Adaptation on Correlated subspace for Unseen Multiview Headpose Classification

Image Completion Assisted By Transformation Domain Patch Approximation

Table Extraction from Document Images using Fixed Point Model

A Novel Method for Face Track Linking in Videos

CRF Based Frontier Detection using Monocular Camera

Interest Point Detection in Videos Using Long Point Trajectories

Scene Text Analysis using Deep Belief Networks

Content-aware seamless stereoscopic 3D compositing

Short Local Trajectory based moving anomaly detection

Super Pixel Clustering via Kernel Density Estimation

An Improved Harris Corner Detector

3D Face Recognition using Kinect

Recognizing Facial Expressions in the Orthogonal Complement of Principal Subspace

A unified approach to learning depth and motion features

Interactive Simulation of Generalised Newtonian Fluids using GPUs

Shape-from-focus using Total Variation Prior and Split Bregman algorithm

Active gaze stabilization

Secret Image Sharing using Fractal Codes

Improved Weighted Histogram for Illumination Invariant Mean-shift Tracking

Camouflaging Motion Blur: Art or Science?

Enhanced Random Forest for Mitosis Detection

Patch Flow based Visual Object Tracking

3D Object Super Resolution using Metric Tensor and Christoffel Symbols

Layered Depth Inference from Flow in Underwater Imagery

High Throughput MR Image Reconstruction Using Compressed Sensing

Robust articulated chain identification via consensual clustering

Scene Text Analysis using Deep Belief Networks

Content Provider	ACM Digital Library
Author	Ray, Anupama Rajeswar, Sai Chaudhury, Santanu
Abstract	This paper focuses on the recognition and analysis of text embedded in scene images using Deep learning. The proposed approach uses deep learning architectures for automated higher order feature extraction, thereby improving classification accuracies in comparison to handcrafted features used traditionally. Exhaustive experiments have been performed with Deep Belief Networks and Convolutional Deep Neural Networks with varied training algorithms like Contrastive Divergence, De-noising Score Matching and supervised learning algorithms such as logistic regression and Multi-layer perceptron. These algorithms have been validated on 4 standard datasets: Chars 74K English, Chars 74K Kannada, ICDAR 2003 Robust OCR dataset and SVT-CHAR dataset. The proposed network achieves improved recognition results on Chars74K English, Kannada and SVT-CHAR dataset in comparison to the state-of-art algorithms. For ICDAR 2003 dataset, the proposed network is marginally worse in comparison to Deep Convolutional networks. Although deep belief networks have been considerably used for several applications, according to the knowledge of the authors, this is the first paper to report scene text recognition using deep belief networks.
Starting Page	1
Ending Page	8
Page Count	8
File Format	PDF
ISBN	9781450330619
DOI	10.1145/2683483.2683554
Language	English
Publisher	Association for Computing Machinery (ACM)
Publisher Date	2014-12-14
Publisher Place	New York
Access Restriction	Subscribed
Subject Keyword	Scene text recognition Deep belief networks Deep convolutional neural network Restricted boltzmann machines
Content Type	Text
Resource Type	Article

Central Library (ISO-9001:2015 Certified)
Indian Institute of Technology Kharagpur
Kharagpur, West Bengal, India | PIN - 721302

See location in the Map
03222 282435
Mail: support@ndl.gov.in

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in