Word Recognition of Indic Scripts Naveen TS CVIT

Word Recognition of Indic Scripts Naveen TS CVIT

Word Recognition of Indic Scripts Naveen TS CVIT IIIT Hyderabad IIIT Hyderabad Introduction 22 official languages. 100+ languages. Language specific number system. Two major groups Indo Aryan Dravidian IIIT Hyderabad Optical Character Recognition IIIT Hyderabad OCR Challenges

Challenges due to text editors Different editors renders same symbol in different ways. Multiple fonts Poor/cheap printing technology IIIT Hyderabad Can cause degradations like Cuts/Merges Scanning quality IL Script Complexity Script complexity Matras, similar looking characters IIIT Hyderabad Samyuktakshar UNICODE re-ordering

Unicode re-ordering Final Output IIIT Hyderabad OCR Development challenges Word -> Symbol segmentation Presence of cuts/merges Development of a strong classifier Efficient post-processor Porting of technology for development of OCR for a new language. IIIT Hyderabad Motivation for this Thesis Avoiding the tough word->symbol

segmentation Automatic learning of latent symbol -> UNICODE conversion Common architecture for multiple languages Post-processor development challenges for highly inflectional languages. IIIT Hyderabad OCR DEVELOPMENT IIIT Hyderabad Recognition Architecture Large # Output Classes Huge training size Degradation impact minimal Word Recognizer

Small # Output Classes Moderate training size Degradation impact serious Symbol Recognizer IIIT Hyderabad Limitation of Char recognition System Difficult to obtain annotated training samples Extracting symbols from words is tough. Inability to utilize all available training data Extremely difficult to extract all symbols from 5000 pages and annotate them.

Classifier output(Char) -> Required output(Word) conversion. Issues due to degradations (Cuts/Merges) etc. IIIT Hyderabad Holistic Recognition Word Annotation Word Text Word Image Word Recognition System IIIT Hyderabad To Evaluation System Evaluation Final Output

BLSTM Workflow Word Output Output layer CTC LSTM Cell CTC backward pass Hiddenlayers layers Hidden

Input layer forward pass t+1 t Input sequence Features IIIT Hyderabad Importance of Context Small Context Larger Context For a given feature, BLSTM takes into account forward as well as backward context.

IIIT Hyderabad BLSTM for Devanagari Motivation No Zoning Word Recognition Handle large # classes IIIT Hyderabad Naveen Sankaran and C V Jawahar. Recognition of Printed Devanagari Text Using BLSTM Neural Network International Conference on Pattern Recognition(ICPR), 2012. BLSTM for Devanagari Feature Extraction Input Image BLSTM Network

Output Class Labels 35, 64, 55, 105 Class Label to Unicode conversion IIIT Hyderabad BLSTM Results Trained on 90K words and tested on 67K words. Obtained more than 20% improvement in Word Error Rate. Char. Error Rate Word Error Rate Devanagari

OCR[1] Ours OCR[1] Ours Good 7.63 5.65 17.88 8.62 Poor 20.11

15.13 43.15 22.15 IIIT Hyderabad 1. D. Arya, et al., @ ICDAR MOCR Workshop, 2011. Experiences of Integration and Performance Testing of Multilingual OCR for Printed Indian Scripts Qualitative Results IIIT Hyderabad Limitations Symbol to UNICODE conversion rules are required to generate final output. Huge training time of about 2 weeks. IIIT Hyderabad Recognition as Transcription

Network learns how to Transcribe input features to output labels. Target labels are UNICODE No Symbol-> UNICODE output mapping Easily scalable to other languages IIIT Hyderabad Recognition Vs Transcription IIIT Hyderabad Challenges Segmentation free training and testing UNICODE (akshara) training and UNICODE (akshara) testing Practical Issues: Learning with memory: (symbol ordering in Unicode) Large output label space Scalability to large data set Efficiency in testing IIIT Hyderabad

Training time Training time increases when # Output classes increases # Features decreases # Training data increases IIIT Hyderabad Training at Unicode level UNICODE training largely reduces the number of classes. Language # Unicode # Symbols Malayalam 163

215 Tamil 143 212 Telugu 138 359 Kannada 156 352 UNICODE training can reduce the time taken IIIT Hyderabad

Features Each word split horizontally into two parts 7 features extracted from top and bottom half Sliding window of size 5pixel used. Binary Features Grey Features Mean Std. Deviation IIIT Hyderabad Variance Network Configuration IIIT Hyderabad

Learning rate of 0.0009 Momentum 0.9 Number of hidden layers = 1 Number of nodes in hidden layer = 100 IIIT Hyderabad Input t=0 Input layer Hidden Layer Output Layer . .

. CTC . . . LAYER Final Network Architecture UNICODE Output Evaluation & Results IIIT Hyderabad Dataset Annotated Multi-lingual Dataset (AMD) Annotated DLI dataset (ADD) 1000 Hindi pages from DLI

IIIT Hyderabad Language No. of Books No. of Pages Hindi 33 5000 Malayalam 31 5000

Tamil 23 5000 Kannada 27 5000 Telugu 28 5000 Gurumukhi 32 5000

Bangla 12 1700 AMD ADD Evaluation Measure IIIT Hyderabad Quantitative Results Language Character Error Rate(CER) Our Char OCR[1] Tesseract[2] Method

Word Error Rate(WER) Our Char Method OCR[1] Tesseract[2] Hindi 6.38 12.0 20.52 25.39 38.61 34.44 Malayalam

2.75 5.16 46.71 10.11 23.72 94.62 Tamil 6.89 13.38 41.05 26.49 42.22

92.37 Telugu 5.68 24.26 39.48 16.27 71.34 76.15 Kannada 6.41 16.13

- 23.83 48.63 - Bangla 6.71 5.24 53.02 21.68 24.19 84.86 Gurumukhi

5.21 5.58 - 13.65 25.72 - IIIT Hyderabad 1. D. Arya, et al., @ ICDAR MOCR Workshop, 2011. Experiences of Integration and Performance Testing of Multilingual OCR for Printed Indian Scripts 2. https://code.google.com/p/tesseract-ocr/ Qualitative Results IIIT Hyderabad

Performance with Degradation Added Synthetic degradation to words and evaluated them. Degradation Level 1 Degradation Level 2 Degradation Level 3 IIIT Hyderabad Qualitative Results Unicode Rearranging IIIT Hyderabad Error Detection for Indian Languages IIIT Hyderabad

Error Detection : Why is it hard? Highly Inflectional UNICODE Vs Akshara Words can be joined to from another valid new word. IIIT Hyderabad Development Challenges Availability of large corpus Percentage of unique words IIIT Hyderabad Language Total Words Unique Words Average Word Length

Hindi 4,626,594 296,656 (6.42%) 3.71 Malayalam 3,057,972 912,109 (29.83%) 7.02 Kannada 2,766,191 654,799 (23.67%) 6.45

Tamil 3,763,587 775,182 (20.60%) 6.41 Telugu 4,365,122 1,117,972 (25.62%) 6.36 English 5,031,284 247,873 (4.93%)

4.66 Development Challenges # Unique words in Indian Languages IIIT Hyderabad Development Challenges Word Coverage IIIT Hyderabad Corpus % Malayalam Tamil Kannada Telugu Hindi

English 10 71 95 53 103 7 8 20 491 479

347 556 23 38 30 1969 1541 1273 2023 58 100 40

6061 4037 3593 5748 159 223 50 16,555 9680 8974 14,912

392 449 60 43,279 22,641 21,599 38,314 963 988 70 114,121 54,373

53,868 101,110 2395 2573 80 300,515 140,164 144,424 271,474 6616 8711

Error Models for IL OCR Two type of errors generated by OCR Non-Word error Presence of impossible symbols between words. Caused due to recognition issues, Symbol -> UNICODE mapping issues etc. IIIT Hyderabad Error Models for IL OCR Two type of errors generated by OCR Real-Word error Caused when one valid symbol is recognized as another valid symbol. Mainly caused due to confusion among symbols IIIT Hyderabad Error Models for IL OCR

Percentage of words which gets converted to another word for a give Hamming distance. IIIT Hyderabad Error Detection Methods IIIT Hyderabad Using Dictionary Create a dictionary based on most frequently occurring words. Valid words are those which are present . Accuracy depends on dictionary coverage. Using akshara nGram Generate symbol (akshara) nGram based dictionary. Every word is converted to its associated nGrams. Dictionary generated using these nGrams. A word is valid if all nGrams are present in dictionary. Error Detection Methods Word and akshara dictionary combination First check if word is present in dictionary.

If not, check in the nGram dictionary. IIIT Hyderabad Detection through learning Use linear classification methods to classify a word as valid or invalid. nGram probabilities are chosen as features. Used SVM based binary classifier to train. This model was used to predict if a word was valid or not. Evaluation Matrix True Positive (TP) : Our model detect a word as Invalid and annotation seconds it False Positive(FP) : Our model detect a word as Invalid but is actually a valid word True Negative (FN) : Our model detects a word as Valid but is actually invalid word False Negative (TN) : Our model detects a word as Valid and annotation seconds it Precision, Recall and F-Score IIIT Hyderabad

Dataset British National Corpus for English and CIIL corpus for Indian Languages. Used OCR output from Arya et.al (J-MOCR, ICDAR 2011) for experiments. Took 50% wrong OCR outputs to train SVM with negative samples. Malayalam dictionary size of 670K words and Telugu dictionary size of 700K IIIT Hyderabad Results Method Malayalam Telugu TP FP

TN FN TP FP TN FN Word Dictionary 72.36 22.88 77.12 27.63 94.32

92.13 7.87 5.67 nGram Dictionary 72.85 22.17 77.83 27.15 62.12 6.37 93.63

37.88 Word Dict. + nGram 67.97 14.95 85.04 32.02 65.01 2.2 97.8 34.99 Word Dictionary + SVM

62.87 9.73 90.27 37.13 68.48 3.24 96.76 31.52 Table showing TP,FP,TN and FN values for Malayalam and Telugu Malayalam Method Telugu IIIT Hyderabad

Precision Recall F-Score Precision Recall F-Score Word Dictionary 0.52 0.72 0.60 0.51 0.94

0.68 nGram Dictionary 0.53 0.73 0.61 0.91 0.62 0.73 Word Dict. + nGram 0.61 0.68 0.74

0.94 0.64 0.76 Word Dictionary + SVM 0.69 0.63 0.76 0.95 0.67 0.78 Table showing Precision, Recall and F-Score values for Malayalam and Telugu

Conclusion A generic OCR framework for multiple Indic Scripts. Recognition as Transcription. Holistic recognition with UNICODE output. High accuracy without any post-processing. IIIT Hyderabad Understanding challenges in developing postprocessor for Indic Scripts. Error detection using machine learning. Thank You !!!! IIIT Hyderabad

Recently Viewed Presentations

  • Toward a Sustainable Wellbeing Economy How behavioral economics

    Toward a Sustainable Wellbeing Economy How behavioral economics

    A teleological version of evolution? From Darwin's idea of natural selection we get the idea that the best adapted individuals in the face of competition for limited resources in the face of Malthusian pressure comes the idea of 'survival of...
  • Morphological and Syntactic Analysis

    Morphological and Syntactic Analysis

    Outline: Morphology. Morphemic segmentation. un + beat + able. Phonology ("morphonology") and orthography. bab. y + s = bab. ie. s. Inflectional vs. derivational morphology. Morphological analysis: word form lemma + morphosyntactic features (tag) Tagging (context-aware disambiguation) Unsupervised affix detection...
  • WAVE MECHANICS (Schrödinger, 1926) - Unical

    WAVE MECHANICS (Schrödinger, 1926) - Unical

    WAVE MECHANICS (Schrödinger, 1926) The currently accepted version of quantum mechanics which takes into account the wave nature of matter and the uncertainty principle. * The state of an electron is described by a function y, called the "wave function"....
  • The Color Quiz - Tuscaloosa County School District

    The Color Quiz - Tuscaloosa County School District

    Sensing/Intuition (S or N) What is it? How we process information! Sensing: Using our 5 senses (touch, taste, smell, sight, and sound) to make decisions and think about our world
  • Bridget Jones: os novos caminhos de Lizzy Bennet

    Bridget Jones: os novos caminhos de Lizzy Bennet

    Bridget Jones: os novos caminhos de Lizzy Bennet. Sabine Mendes Lima Moura, Dn. Cinemateca Literária. Universidade Veiga de Almeida. 1/2012 "Quando eu era jovem, nunca precisava de ninguém e fazer amor era só por diversão - esses dias acabaram"
  • Arterial Blood Gas Analysis - EmergencyPedia

    Arterial Blood Gas Analysis - EmergencyPedia

    Arial MS Pゴシック Calibri Chalkboard Symbol Monotype Sorts Office Theme Arterial Blood Gas Analysis What is an ABG? Why Order an ABG? Logistics Acid Base Balance Acid Base Balance The Terms Respiratory Acidosis Respiratory Acidosis Respiratory Alkalosis Respiratory Alkalosis Metabolic...
  • Once youre in, youre in. When the bell

    Once youre in, youre in. When the bell

    THREE weeks left in the quarter - if your name is on the board , you owe me a quiz or a test!! If you have a zero and you think you turned it in I have passed it back...
  • Chapter 9: Circulation: The Cardiovascular and Lymphatic Systems

    Chapter 9: Circulation: The Cardiovascular and Lymphatic Systems

    Terms. Meaning. appendix. A small, finger-like mass of lymphoid tissue attached to the first part of the large intestine. lymph. The thin plasma-like fluid that drains from the tissues and is transported in lymphatic vessels (root: lymph/o) lymph node