A Global Initiative of Academic Networks (GIAN) Course on

Analysis and Applications of Document Image Processing

4th December 2017 - 8th December 2017

Schedule Download BrochurePayment Details

Overview

With the evolution of mobile devices and fast computers, an increasing interest has been fostered in document image analysis. With many paper documents being sent and received via fax machines and being stored digitally in large document databases, the interest grew to do more with these images than simply view and print them. Just as humans extract information from these images, research was performed and commercial systems built to read text on a page, to find fields on a form, and to locate lines and symbols on a diagram. Today, the results of research work in document processing and optical character recognition (OCR) can be seen and felt every day.

Industrial automation is recognizing text on maps, houses, packages and containers has broad applications related to industrial automation. For example, automatic identification of container numbers improves logistics efficiency.  Recognition of addresses on envelopes is applied in mail sorting systems to automatically route mails in post offices. Recognition of house numbers and text in maps benefits automatic geocoding systems. Engineering diagrams are extracted from paper for computer storage and modification.

In multi-lingual and multi-script countries like India, information communication using multiple languages/scripts is quite common. Due to complex nature of Indic scripts, recognition of such scripts is required for automation of Indic documents. Many industries and organizations are working in automation of various applications using document images techniques. This course will discuss the techniques of document image processing and its real-world applications in industry.

Objectives

Modules

Who can Attend

Executives, engineers and researchers from manufacturing, service and government organizations including R&D laboratories.

Student students at all levels (BTech/MSc/MTech/PhD) or Faculty from reputed academic institutions and technical institutions.

Eligibility

Faculty members and students from academic Institutions (Technical Institutes/Universities) and Industry/Research organizations involved in image processing, computer vision, pattern recognition.

Fees

The participation fees for taking the course is as follows:
Participants from abroad : US $200
Students : Rs 4000
Faculty/Staff of Academic Institutions: Rs. 6000
Industry/Research Personnel: Rs. 8000
The above fee include all instructional materials, computer use for tutorials and assignments, laboratory equipment usage charges, 24 hr free internet facility. Limited accommodation will be provided. Please send your request by Nov 22nd. Registration portal will be open till Nov 15th. Limited seats are available.

Faculty

Prof. J. Llados

Prof. J. Llados is an Associate Professor at the Computer Sciences Department of the Universitat Autònoma de Barcelona and a staff researcher of the Computer Vision Center, where he is also the director since January 2009. His current research fields are document analysis, structural and syntactic pattern recognition and computer vision.

Dr. P. P. Roy

Dr. P. P. Roy is an Assistant Professor at Dept. of Computer Science and Engineering, Indian Institute of Technology, Roorkee. His research interest is Pattern Recognition and Image Analysis.

Dr. R. Balasubramanian

Dr. R. Balasubramanian is an Associate Professor Dept. of Computer Science and Engineering, Indian Institute of Technology, Roorkee. His research interest is in the areas of Computer Vision, Graphics and Image Processing.

Tentative Lecture Schedule

Day 1

Lecture 1: 1 hrs:

Basic principles of Optical Character Recognition (OCR), document understanding, layout-analysis, character and symbol recognition.

Lecture 2: 1 hrs:

Graphics recognition, administrative document retrieval using graphical entities, textextraction in map documents.

Tutorial 1: 2 hrs

Problem solving session with examples: Page layout analysis, feature extraction, recognition of characters and symbols.

Day 2

Lecture 3: 1 hrs:

Word spotting in document images, query by example, query by text, relevance-feedback, query fusion, re-ranking strategies.

Lecture 4: 1 hrs:

Image pre-processing techniques, edge detection, image filtering, image segmentation.

Tutorial 2: 2 hrs

Problem solving session with examples: Word recognition, spotting, query by example, re-ranking of relevant results.

Day 3

Lecture 5: 1 hrs:

Historical document analysis, line segmentation, separation of overlapping text, touching characters.

Lecture 6: 1 hrs:

Feature extraction techniques using shape, color and texture.

Tutorial 3: 2 hrs

Problem solving session with examples: Different filtering techniques, image de-noising methods, feature extraction techniques in spatial and frequency domain.

Day 4

Lecture 7: 1 hrs:

Graph-based document analysis, symbol/character matching using graphs, spotting of symbol in large documents by graph-based approach.

Lecture 8: 1 hrs:

Text detection in natural scene images and videos, problem of multi-orientation in text, and low resolution images.

Tutorial 4: 2 hrs

Problem solving session with examples: structural feature extraction, symbol matching using graphs, graph based symbol detection.

Day 5

Lecture 9: 1 hrs:

Applications of document image processing transferred to Industry, Historical documentarchive analysis, virtual reality in architectural floor plan, document searching using entities suchas logo, seals.

Lecture 10: 1 hrs:

Indic script identification and recognition, Segmentation techniques of text in Indicscripts, Various features developed for Indic script recognition.

Tutorial 5: 2 hrs

Problem solving session with examples: Script identification, segmentation, feature extraction and recognition for low-resolution images.