Online recognition algorithm. LEARNING Letters raw data.

Slides:



Advertisements
Similar presentations
FEATURE PERFORMANCE COMPARISON FEATURE PERFORMANCE COMPARISON y SC is a training set of k-dimensional observations with labels S and C b C is a parameter.
Advertisements

QR Code Recognition Based On Image Processing
Face Recognition and Biometric Systems Eigenfaces (2)
Curse of Dimensionality Prof. Navneet Goyal Dept. Of Computer Science & Information Systems BITS - Pilani.
ONLINE ARABIC HANDWRITING RECOGNITION By George Kour Supervised by Dr. Raid Saabne.
Imbalanced data David Kauchak CS 451 – Fall 2013.
Data Mining Methodology 1. Why have a Methodology  Don’t want to learn things that aren’t true May not represent any underlying reality ○ Spurious correlation.
Recovering Human Body Configurations: Combining Segmentation and Recognition Greg Mori, Xiaofeng Ren, and Jitentendra Malik (UC Berkeley) Alexei A. Efros.
Image Analysis Phases Image pre-processing –Noise suppression, linear and non-linear filters, deconvolution, etc. Image segmentation –Detection of objects.
G. Alonso, D. Kossmann Systems Group
Model generalization Test error Bias, variance and complexity
Minimum Redundancy and Maximum Relevance Feature Selection
Data preprocessing before classification In Kennedy et al.: “Solving data mining problems”
Chapter 7 – Classification and Regression Trees
Chapter 7 – Classification and Regression Trees
Low Complexity Keypoint Recognition and Pose Estimation Vincent Lepetit.
Addressing the Medical Image Annotation Task using visual words representation Uri Avni, Tel Aviv University, Israel Hayit GreenspanTel Aviv University,
AUTOMATIC SPEECH CLASSIFICATION TO FIVE EMOTIONAL STATES BASED ON GENDER INFORMATION ABSTRACT We report on the statistics of global prosodic features of.
1 The (“Sampling”) Distribution for the Sample Mean*
Active Learning. 2 Learning from Examples  Passive learning A random set of labeled examples A random set of labeled examples.
March 15-17, 2002Work with student Jong Oh Davi Geiger, Courant Institute, NYU On-Line Handwriting Recognition Transducer device (digitizer) Input: sequence.
Pattern Classification All materials in these slides were taken from Pattern Classification (2nd ed) by R. O. Duda, P. E. Hart and D. G. Stork, John.
Learn how to make your drawings come alive…  NEW COURSE: SKETCH RECOGNITION Analysis, implementation, and comparison of sketch recognition algorithms,
Jeff Howbert Introduction to Machine Learning Winter Machine Learning Feature Creation and Selection.
Handwritten Character Recognition using Hidden Markov Models Quantifying the marginal benefit of exploiting correlations between adjacent characters and.
By George Kour Supervised By: Prof. Dana Ron Dr. Raid Saabne
Face Detection CSE 576. Face detection State-of-the-art face detection demo (Courtesy Boris Babenko)Boris Babenko.
1 Linear Methods for Classification Lecture Notes for CMPUT 466/551 Nilanjan Ray.
Convolutional Neural Networks for Image Processing with Applications in Mobile Robotics By, Sruthi Moola.
Module 04: Algorithms Topic 07: Instance-Based Learning
Masquerade Detection Mark Stamp 1Masquerade Detection.
Testing. Definition From the dictionary- the means by which the presence, quality, or genuineness of anything is determined; a means of trial. For software.
This week: overview on pattern recognition (related to machine learning)
Efficient Model Selection for Support Vector Machines
Introduction to variable selection I Qi Yu. 2 Problems due to poor variable selection: Input dimension is too large; the curse of dimensionality problem.
ADVANCED CLASSIFICATION TECHNIQUES David Kauchak CS 159 – Fall 2014.
Simple Image Processing Speaker : Lin Hsiu-Ting Date : 2005 / 04 / 27.
Recognition using Regions (Demo) Sudheendra V. Outline Generating multiple segmentations –Normalized cuts [Ren & Malik (2003)] Uniform regions –Watershed.
Chapter 9 – Classification and Regression Trees
Classification and Ranking Approaches to Discriminative Language Modeling for ASR Erinç Dikici, Murat Semerci, Murat Saraçlar, Ethem Alpaydın 報告者:郝柏翰 2013/01/28.
Particle Filters for Shape Correspondence Presenter: Jingting Zeng.
Data Reduction. 1.Overview 2.The Curse of Dimensionality 3.Data Sampling 4.Binning and Reduction of Cardinality.
Hypothesis Testing A procedure for determining which of two (or more) mutually exclusive statements is more likely true We classify hypothesis tests in.
Multiple alignment: Feng- Doolittle algorithm. Why multiple alignments? Alignment of more than two sequences Usually gives better information about conserved.
LARGE MARGIN CLASSIFIERS David Kauchak CS 451 – Fall 2013.
Ch 4. Linear Models for Classification (1/2) Pattern Recognition and Machine Learning, C. M. Bishop, Summarized and revised by Hee-Woong Lim.
Presented at SCANGIS 97 On the improving of elevation accuracy of Digital Elevation Models: a comparison of some error detection procedures Carlos López.
ISOMAP TRACKING WITH PARTICLE FILTER Presented by Nikhil Rane.
11/23/2015Slide 1 Using a combination of tables and plots from SPSS plus spreadsheets from Excel, we will show the linkage between correlation and linear.
Introduction to Inference: Confidence Intervals and Hypothesis Testing Presentation 4 First Part.
CSC508 Convolution Operators. CSC508 Convolution Arguably the most fundamental operation of computer vision It’s a neighborhood operator –Similar to the.
Gesture Input and Gesture Recognition Algorithms.
Chapter1: Introduction Chapter2: Overview of Supervised Learning
A New Approach to Utterance Verification Based on Neighborhood Information in Model Space Author :Hui Jiang, Chin-Hui Lee Reporter : 陳燦輝.
Notes on HW 1 grading I gave full credit as long as you gave a description, confusion matrix, and working code Many people’s descriptions were quite short.
LIGO-G Z r statistics for time-domain cross correlation on burst candidate events Laura Cadonati LIGO-MIT LSC collaboration meeting, LLO march.
Hidden Markov Model Parameter Estimation BMI/CS 576 Colin Dewey Fall 2015.
Data Transformation: Normalization
MIRA, SVM, k-NN Lirong Xia. MIRA, SVM, k-NN Lirong Xia.
Convolutional Networks
Machine Learning Feature Creation and Selection
K Nearest Neighbor Classification
ECE539 final project Instructor: Yu Hen Hu Fall 2005
Lesson Comparing Two Means.
Connecting Data with Domain Knowledge in Neural Networks -- Use Deep learning in Conventional problems Lizhong Zheng.
Model Evaluation and Selection
Handwritten Characters Recognition Based on an HMM Model
Feature Selection Methods
MIRA, SVM, k-NN Lirong Xia. MIRA, SVM, k-NN Lirong Xia.
Evaluation David Kauchak CS 158 – Fall 2019.
Presentation transcript:

Online recognition algorithm

LEARNING

Letters raw data

Building the Letters Dictionary For each Letter For Each Position The outcome of this process is 4 kdtree data structures for each Letters Position. – And some extra data as the coeff matrix of PCA and LDA

RECOGNITION

Online Recognition process Overview

Segmentation and recognition is done while the word is being scribed.

Demarcation points are residents of Horizontal segments. Horizontal Segment: – Low Slope – Forward (right to Left) We look for horizontal segments while progressing.

Legend Green – Horizontal Segment start (StartHS) Black – Horizontal Segment End (EndHS) Blue – Candidate Point Red – Segmentation Point

MidPoint – is the medial point between the StartHS and the EndHS. MidPoint is classified as Candidate Point or Cratical Point. Horizontal segment detected. Set as candidate point.

The classified subsequence is always from the last segmentation point to current candidate point.

Conditions of Start HS: – Small slope. – The simplified sequence contains more than 3 points. To make sure the sequence contain enough info. – The direction of the line is right to left. – The segmentation point is on the baseline (Effective from the 3’rd candidate point.)

Conditions of EndHS – High slope Or directed Backwards. – Take the last seen horizontal point to be EndHS point.

Start Horizontal Segment

End Horizontal Segment. Choose the best segmentation point between the last 2 candidate points. In this case, the second candidate point was taken as the segmentation point.

The first point represents the subsequence: 0 - blue point. The second point represent the subsequence: 0 - red point. Now there is no candidate point since the second candidate was selected as the segmentation points.

The candidates are the 3-NN. Each candidate has a classification score. The candidate point with the minimum classification score is selected.

MouseUp: The event of ending a stroke. If there is no candidate point: – Option 1: The last point is a demarcation point. – Option 2: Demarcation point translation.

If there is a candidate point – Option 1: Both the candidate point and the last point are demarcation points – Option 2: only the last point is a demarcation point.

In this case Option 1 was selected. Mouse UP - In special cases a critical point translation was implemented. – If the Last segmentation point is too close to the MouseUp event

Preprocessing Every Sequence passes through 3 filters in the following order: – Normalization – Simplification Using Recursive Douglas-Peucker Polyline Simplification. Proportional Sensitivity parameter: Absolute Sensitivity Parameter: – Resampling Using splines. Classification resampling size: 40 (points) Processing resampling size: #proptional*5

In-progress Baseline detection Segmentation points are usually placed on the baseline. 2 or more segmentation points define the word baseline. Find the baseline using linear regression. A new segmentation point is nominated only of it is sufficiently close to the baseline.

Classification A separate data structure for each position. Feature: shape context. Approx. EMD Embedding – coif1/coif2. K-NN data structure: kdtree.

Dimensionality Reduction We use PCA in the first phase and LDA in the second phase. PCA data preservation rate=0.98 LDA Reduces 1 dimension. We achieved ~8-13 dimensions. (Depending on the position)

Limitations A stroke (sequence) always contains a WP. – A letter is written is a single stroke. We don’t handle additional strokes Special cases we don’t handle: – Letters like س, which can be recognized as a sequence of 2 or 3 ب. – We do not differentiate between ط and ص. – We do not have ن and ي in Mid and Ini position in the validation test, as both can’t be differentiate from ب Very small sample set. – ~7 samples for each class. Interesting to see how the system will behave when we will have much larger samples for each class. – We expect to have minimum of 20 samples for each letter class.

Test Setup Test set size: 521 WPs Average WP length 4.9 [letters]. Number of letters samples: 7. The WP length is distributed uniformly. We evaluate recognition rate and segmentation rates. Recognition parameters: – K = 10 – Max slope: 0.5 – Max deviation from baseline = 0.15 Method – Blind Test. (leave one out) Top 3 – if one of the top 3 suggestion is correct => the letter was classified correctly. Nor Test WP Neither training letter set do not contain the following letters: –ط ء لا ـك ـكـ س ( كـ is included)

Results Segmentation Rate [%] Recognition Rate [%] AVG Recognition time [sec] Blind Test (sample 2) Blind Test (sample 4) Blind Test (sample 6) Blind Test (sample 7) Average Leave one out Seen Letters

Conclusion Good Performance. – We assume it will stay low even when we have a large training set – kdtree & low number of dimensions. Fair recognition and segmentation percentage, considering the following facts: – Some generated words are distorted and almost unreadable by human. – Very few training samples. We need more training data.

Enhancements Improve the segmentation point selection – Try to the learn the region of the segmentation point and use it to give scores to the segmentation points candidates. Features: shape context Or angles Classification: 2-class SVM – Validate the segmentation point is not in a loop.

Enhancements Cont. Adjust the legal slope range according to the baseline slope. Waive the assumption that a stroke contains a WP, i.e. has the following structure: [Ini,Med*,Fin]. --Done Waive the assumption that a letter is written in a single stroke. Add Ligatures - complex Letters such as لما and محـ. Code and performance Refactoring!

LIVE DEMO