An Adaptive Image Enhancement Algorithm for Face Detection By Lizuo Jin, Shin’ichi Satoh, and Masao Sakauchi. ECE 738 In Young Chung.

Slides:



Advertisements
Similar presentations
QR Code Recognition Based On Image Processing
Advertisements

Embedded Image Processing on FPGA Brian Kinsella Supervised by Dr Fearghal Morgan.
Digital Image Processing
Grey Level Enhancement Contrast stretching Linear mapping Non-linear mapping Efficient implementation of mapping algorithms Design of classes to support.
CS & CS Multimedia Processing Lecture 2. Intensity Transformation and Spatial Filtering Spring 2009.
Intensity Transformations (Chapter 3)
Digital Image Processing
Intensity Transformations
Digital Image Processing
Image Processing IB Paper 8 – Part A Ognjen Arandjelović Ognjen Arandjelović
Image Enhancement by Modifying Gray Scale of Individual Pixels
Digital Image Processing In The Name Of God Digital Image Processing Lecture3: Image enhancement M. Ghelich Oghli By: M. Ghelich Oghli
Face Recognition and Biometric Systems 2005/2006 Filters.
Foreground Background detection from video Foreground Background detection from video מאת : אבישג אנגרמן.
A Review of “Adaptive fingerprint image enhancement with fingerprint image quality analysis”, by Yun & Cho Malcolm McMillan.
Lecture 5 Template matching
Modeling Pixel Process with Scale Invariant Local Patterns for Background Subtraction in Complex Scenes (CVPR’10) Shengcai Liao, Guoying Zhao, Vili Kellokumpu,
Segmentation Divide the image into segments. Each segment:
Digital Image Processing
Face Detection: a Survey Speaker: Mine-Quan Jing National Chiao Tung University.
1 Lecture 12 Neighbourhood Operations (2) TK3813 DR MASRI AYOB.
CS 376b Introduction to Computer Vision 02 / 25 / 2008 Instructor: Michael Eckmann.
1 Integration of Background Modeling and Object Tracking Yu-Ting Chen, Chu-Song Chen, Yi-Ping Hung IEEE ICME, 2006.
Image Enhancement.
Lecture 2. Intensity Transformation and Spatial Filtering
Chapter 5 Image Restoration. Preview Goal: improve an image in some predefined sense. Image enhancement: subjective process Image restoration: objective.
Despeckle Filtering in Medical Ultrasound Imaging
GmImgProc Alexandra Olteanu SCPD Alexandru Ştefănescu SCPD.
© by Yu Hen Hu 1 ECE533 Digital Image Processing Image Restoration.
CS654: Digital Image Analysis Lecture 17: Image Enhancement.
CIS 601 Image ENHANCEMENT in the SPATIAL DOMAIN Dr. Rolf Lakaemper.
EE663 Image Processing Dr. Samir H. Abdul-Jauwad Electrical Engineering Department King Fahd University of Petroleum & Minerals.
Automatic Minirhizotron Root Image Analysis Using Two-Dimensional Matched Filtering and Local Entropy Thresholding Presented by Guang Zeng.
AdeptSight Image Processing Tools Lee Haney January 21, 2010.
MULTIMEDIA TECHNOLOGY SMM 3001 MEDIA - IMAGES. Processing digital Images digital images are often processed using “digital filters” digital images are.
Bo QIN, Zongshun MA, Zhenghua FANG, Shengke WANG Computer-Aided Design and Computer Graphics, th IEEE International Conference on, p Presenter.
Image Subtraction Mask mode radiography h(x,y) is the mask.
COMP322/S2000/L171 Robot Vision System Major Phases in Robot Vision Systems: A. Data (image) acquisition –Illumination, i.e. lighting consideration –Lenses,
Student Name: Honghao Chen Supervisor: Dr Jimmy Li Co-Supervisor: Dr Sherry Randhawa.
Image Segmentation by Histogram Thresholding Venugopal Rajagopal CIS 581 Instructor: Longin Jan Latecki.
主講者 : 陳建齊. Outline & Content 1. Introduction 2. Thresholding 3. Edge-based segmentation 4. Region-based segmentation 5. conclusion 2.
Digital Image Processing
Digital Image Processing CSC331 Image Enhancement 1.
1 Mathematic Morphology used to extract image components that are useful in the representation and description of region shape, such as boundaries extraction.
Lecture Reading  3.1 Background  3.2 Some Basic Gray Level Transformations Some Basic Gray Level Transformations  Image Negatives  Log.
Digital Image Processing Image Enhancement in Spatial Domain
Adaptive Filter Based on Image Region Characteristics for Optimal Edge Detection Lussiana ETP STMIK JAKARTA STI&K Januari-2012.
Shadow Detection in Remotely Sensed Images Based on Self-Adaptive Feature Selection Jiahang Liu, Tao Fang, and Deren Li IEEE TRANSACTIONS ON GEOSCIENCE.
Image Enhancement Band Ratio Linear Contrast Enhancement
Motion tracking TEAM D, Project 11: Laura Gui - Timisoara Calin Garboni - Timisoara Peter Horvath - Szeged Peter Kovacs - Debrecen.
Image Subtraction Mask mode radiography h(x,y) is the mask.
Heechul Han and Kwanghoon Sohn
IMAGE SEGMENTATION USING THRESHOLDING
PLIP BASED UNSHARP MASKING FOR MEDICAL IMAGE ENHANCEMENT
IMAGE PROCESSING INTENSITY TRANSFORMATION AND SPATIAL FILTERING
Image Enhancement.
Image Analysis Image Restoration.
Dr. Chang Shu COMP 4900C Winter 2008
Image Enhancement in the Spatial Domain
Image Enhancement in the
Lecture 3 (2.5.07) Image Enhancement in Spatial Domain
CSC 381/481 Quarter: Fall 03/04 Daniela Stan Raicu
Presented by :- Vishal Vijayshankar Mishra
Histogram Probability distribution of the different grays in an image.
Digital Image Processing
Grey Level Enhancement
Image Segmentation.
CIS 4350 Image ENHANCEMENT SPATIAL DOMAIN
Chair Professor Chin-Chen Chang Feng Chia University
Intensity Transform Contrast Stretching Y ← u0+γ*(Y-u)/s
Presentation transcript:

An Adaptive Image Enhancement Algorithm for Face Detection By Lizuo Jin, Shin’ichi Satoh, and Masao Sakauchi. ECE 738 In Young Chung

Outline  Motivation – Problem in face detection  Suggestion  Basic idea of suggestion  Approach  Adaptive Image Enhancement Algorithm  Result and Comparison  Conclusion

Problem in Face Detection?  Almost every face-detection methods depends on the intensity values of image  Face detection under unconstrained condition result in failure because of the drastic variation of pixel intensity in face regions  Image enhancement by intensity transformation can reduce this problem, with histogram equalization (HE).  HE applied to images with faces on a very light background, it may produce very dark face regions  face detection failure. HE After Histogram Equalization

Suggestion of solution  Solution? An adaptive image enhancement algorithm which is adapt to the intensity distribution within an image.

Basic idea 1. Why don’t we make it even? Entropy of darker pixels = Entropy of lighter pixels 2. Face is made up of many pixels Face pixels make a cluster in histogram  We can histogram ridge analysis technique

Approaches I.  EER (Entropy Error Rate) as an information theoretic measure represents the tendency of the information distribution within an image If EER is positive and large  the information lies mainly in the darker pixels If EER is negative large  the information is lies mainly in the lighter pixels  Goal : minimizing the EER Where, S : estimate the relative position of the mean in histogram H D,H B : information in darker pixels and lighter pixels respectively H D,H B : the average entropy in either side

Approaches II.  Histogram Ridges Analysis : suggested in the paper “A fast histogram-clustering approach for multi-level thresholding” by Du-Ming Tsau and Ting-Hsiuing Chen  Important parameter: the distance between the leftmost and rightmost ridge because this distance is related with the intensity range of valid content in the image.

Adaptive Enhancement Algorithm Step 1. Extract Intensity Value in the input image

Step 2. Compute the intensity histogram of the input image

Step 3. Threshold the intensity histogram Against noise and stretch to [0,255] Smoothing with Gaussian smoothing Operator with variance = 2.0 Find valid ridges and distance between the ridges (Dr)  this is related with the intensity range of valid content in the image.

Step 4. Filter the histogram obtained in step 2 with a filtering coefficient to eliminate noise or unimportant details

Step 5. Compress the detail region and expend important region by using entropy in darker and lighter side

Step 6. Minimum EER finding process After gamma correction with the parameter obtained in minimum EER F.P

Results Before, Histogram Enhancement After Adaptive Enhancement

Comparison I. Classical histogram equalization (HE) Adaptive histogram enhancement (AE)

Comparison II. Original imageHE AE Image with very light back ground

Conclusion and future works  Image enhancement is very important technique for face detection, especially in the images acquired in unconstrained illumination condition  Unsuitable enhancement can increase detection- failure rate  AE algorithm estimate the image quality base on EER and intensity histogram and select best transform  It performs much better than classical HE method

Question ?