ECE172A Project Report Image Search and Classification Isaac Caldwell.

Slides:

Advertisements

Similar presentations

DECISION TREES. Decision trees  One possible representation for hypotheses.

Advertisements

Unsupervised Learning Clustering K-Means. Recall: Key Components of Intelligent Agents Representation Language: Graph, Bayes Nets, Linear functions Inference.

Image classification Given the bag-of-features representations of images from different classes, how do we learn a model for distinguishing them?

Discriminative Relevance Feedback With Virtual Textual Representation For Efficient Image Retrieval Suman Karthik and C.V.Jawahar.

Patch to the Future: Unsupervised Visual Prediction

Efficient Clustering of High Dimensional Data Sets with Application to Reference Matching ANSHUL VARMA FAISAL QURESHI.

Computer Vision Group, University of BonnVision Laboratory, Stanford University Abstract This paper empirically compares nine image dissimilarity measures.

HCI Final Project Robust Real Time Face Detection Paul Viola, Michael Jones, Robust Real-Time Face Detetion, International Journal of Computer Vision,

1 Chapter 10 Introduction to Machine Learning. 2 Chapter 10 Contents (1) l Training l Rote Learning l Concept Learning l Hypotheses l General to Specific.

Scaling Content Based Image Retrieval Systems Christine Lo, Sushant Shankar, Arun Vijayvergiya CS 267.

CS335 Principles of Multimedia Systems Content Based Media Retrieval Hao Jiang Computer Science Department Boston College Dec. 4, 2007.

Support Vector Machines Pattern Recognition Sergios Theodoridis Konstantinos Koutroumbas Second Edition A Tutorial on Support Vector Machines for Pattern.

Principle of Locality for Statistical Shape Analysis Paul Yushkevich.

Object Recognition Using Distinctive Image Feature From Scale-Invariant Key point D. Lowe, IJCV 2004 Presenting – Anat Kaspi.

Object Class Recognition Using Discriminative Local Features Gyuri Dorko and Cordelia Schmid.

Classification of Remotely Sensed Data General Classification Concepts Unsupervised Classifications.

K-means Based Unsupervised Feature Learning for Image Recognition Ling Zheng.

Exercise Session 10 – Image Categorization

Methods in Medical Image Analysis Statistics of Pattern Recognition: Classification and Clustering Some content provided by Milos Hauskrecht, University.

Pattern Recognition Vidya Manian Dept. of Electrical and Computer Engineering University of Puerto Rico INEL 5046, Spring 2007

Self-organizing Maps Kevin Pang. Goal Research SOMs Research SOMs Create an introductory tutorial on the algorithm Create an introductory tutorial on.

Hierarchical Distributed Genetic Algorithm for Image Segmentation Hanchuan Peng, Fuhui Long*, Zheru Chi, and Wanshi Siu {fhlong, phc,

COMMON EVALUATION FINAL PROJECT Vira Oleksyuk ECE 8110: Introduction to machine Learning and Pattern Recognition.

Bag-of-features models. Origin 1: Texture recognition Texture is characterized by the repetition of basic elements or textons For stochastic textures,

Window-based models for generic object detection Mei-Chen Yeh 04/24/2012.

Implementing Query Classification HYP: End of Semester Update prepared Minh.

Image Classification 영상분류

Ch10 Machine Learning: Symbol-Based

Automatic Image Annotation by Using Concept-Sensitive Salient Objects for Image Content Representation Jianping Fan, Yuli Gao, Hangzai Luo, Guangyou Xu.

BAGGING ALGORITHM, ONLINE BOOSTING AND VISION Se – Hoon Park.

Pattern Recognition April 19, 2007 Suggested Reading: Horn Chapter 14.

1 Pattern Recognition Pattern recognition is: 1. A research area in which patterns in data are found, recognized, discovered, …whatever. 2. A catchall.

Chapter 4: Pattern Recognition. Classification is a process that assigns a label to an object according to some representation of the object’s properties.

CS654: Digital Image Analysis

1Ellen L. Walker Category Recognition Associating information extracted from images with categories (classes) of objects Requires prior knowledge about.

Image Classification for Automatic Annotation

V. Clustering 인공지능 연구실 이승희 Text: Text mining Page:82-93.

Image Classification over Visual Tree Jianping Fan Dept of Computer Science UNC-Charlotte, NC

Clustering Hongfei Yan School of EECS, Peking University 7/8/2009 Refer to Aaron Kimball’s slides.

Aa. Long-term Goal ➲ State the intended goal Customer Wishes ➲ Describe customer needs and wishes ➲ Explain the requirements.

6.S093 Visual Recognition through Machine Learning Competition Image by kirkh.deviantart.com Joseph Lim and Aditya Khosla Acknowledgment: Many slides from.

M ACHINE L EARNING : F OUNDATIONS C OURSE TAU – 2012A P ROF. Y ISHAY M ANSOUR o TextonBoost : Joint Appearance, Shape and Context Modeling for Multi-Class.

Debrup Chakraborty Non Parametric Methods Pattern Recognition and Machine Learning.

Lecture 30: Segmentation CS4670 / 5670: Computer Vision Noah Snavely From Sandlot ScienceSandlot Science.

Lecture 4b Data augmentation for CNN training

Does one size really fit all? Evaluating classifiers in a Bag-of-Visual-Words classification Christian Hentschel, Harald Sack Hasso Plattner Institute.

Introducing a New Product

Nexedi a bunch of great ideas

Semi-Supervised Clustering

A Personal Tour of Machine Learning and Its Applications

IMAGE PROCESSING RECOGNITION AND CLASSIFICATION

Data Driven Attributes for Action Detection

Classification of Remotely Sensed Data

Estimating Link Signatures with Machine Learning Algorithms

Huazhong University of Science and Technology

Self organizing networks

Object detection as supervised classification

Project Implementation for ITCS4122

Machine Learning Week 1.

Boosting Nearest-Neighbor Classifier for Character Recognition

Deep learning Concept Objectives Accomplishments and Impact

Nearest-Neighbor Classifiers

Lecture 22 Clustering (3).

Introduction to Pattern Recognition

5.5 The Marketing Concept The marketing concept is the idea that consumers and competitors should be considered in every important business decision.

Segmentation of Abdominal Adipose Tissues via Deep Learning (基于深度学习的腹内脂肪分割问题） Fei Jiang.

Data Mining (Don’t worry, I am not presenting these slides; just for your reading pleasure)

Face Detection in Color Images

Hubs and Authorities & Learning: Perceptrons

Presentation transcript:

ECE172A Project Report Image Search and Classification Isaac Caldwell

Motivation Develop image processing algorithms that allow searching directly on the image, not in the image tags. The basic concept is a 2D Google search.

Related Research Perona/CalTech – Unsupervised. Boutell/UofRochester – Trained with whole images.

Approach Unsupervised approach relies on heavier processing. Not going anywhere in 4 weeks. Training  Features: complexity and color.  K-means separation fails as sample space overlaps. No distinct clusters.  Nearest Neighbor requires delineating training sets.

Cost Analysis Indicate the financial advantages for the customer Compare quality and price with those of the competition

High-level Representation...

Processing

Results Not so great..

Results Three Categories: Sky, Foliage, Dirt

Results Closeup of the last slide...

Improvements Expand the training data and improve its quality. Adding detected sector properties ( beyond {E,R,G,B}.) Kill the nasty bug in the entropy scaling.

Closing Replace the core engine.  The concept of an “image-in, image-out” search engine really needs to be unsupervised.  The implementation has potential as a segmentation scheme.  Some work on the mapping output could be used as an image classifier (lots of sky or lots of dirt).