Outline of object recognition Learning

- 11.36

Deep-learning algorithm predicts photos' memorability at “near ...
photo src: news.mit.edu

The following outline is provided as an overview of and topical guide to object recognition:

Object recognition - technology in the field of computer vision for finding and identifying objects in an image or video sequence. Humans recognize a multitude of objects in images with little effort, despite the fact that the image of the objects may vary somewhat in different view points, in many different sizes and scales or even when they are translated or rotated. Objects can even be recognized when they are partially obstructed from view. This task is still a challenge for computer vision systems. Many approaches to the task have been implemented over multiple decades.


Intro to Deep Learning for Computer Vision
photo src: chaosmail.github.io


Maps, Directions, and Place Reviews



Approaches based on CAD-like object models

  • Edge detection
  • Primal sketch
  • Marr, Mohan and Nevatia
  • Lowe
  • Olivier Faugeras

Recognition by parts

  • Generalized cylinders (Thomas Binford)
  • Geons (Irving Biederman)
  • Dickinson, Forsyth and Ponce

Object Detection Deep Learning Video



Appearance-based methods

- Use example images (called templates or exemplars) of the objects to perform recognition

- Objects look different under varying conditions:

- A single exemplar is unlikely to succeed reliably. However, it is impossible to represent all appearances of an object.

1. Edge matching

2. Divide-and-Conquer search

3. Greyscale matching

4. Gradient matching

5. Histograms of receptive field responses

6. Large modelbases


Object Recognition using deep learning (testing data) - YouTube
photo src: www.youtube.com


Feature-based methods

- a search is used to find feasible matches between object features and image features.

- the primary constraint is that a single position of the object must account for all of the feasible matches.

- methods that extract features from the objects to be recognized and the images to be searched.

1. Interpretation trees

  • Nodes are "pruned" when the set of matches is infeasible.
  • Historically significant and still used, but less commonly

2. Hypothesize and test

3. Pose consistency

  • Use the smallest number of correspondences necessary to achieve discrete object poses

4. Pose clustering

  • These improvements are sufficient to yield working systems

5. Invariance

6. Geometric hashing

7. Scale-invariant feature transform (SIFT)

8. Speeded Up Robust Features (SURF)

Bag of words representations


Intro to Deep Learning for Computer Vision
photo src: chaosmail.github.io


Genetic algorithm

Genetic algorithms can operate without prior knowledge of a given dataset and can develop recognition procedures without human intervention. A recent project achieved 100 percent accuracy on the benchmark motorbike, face, airplane and car image datasets from Caltech and 99.4 percent accuracy on fish species image datasets.


pdollar | Learning to See
photo src: pdollar.wordpress.com


Other approaches


Simple Pictures That State-of-the-Art AI Still Can't Recognize | WIRED
photo src: www.wired.com


Applications

Object recognition methods has the following applications:


YOLO: Real-Time Object Detection
photo src: pjreddie.com


Surveys

  • Daniilides and Eklundh, Edelman.
  • Roth, Peter M. & Winter, Martin (2008). "SURVEYOFAPPEARANCE-BASED METHODS FOR OBJECT RECOGNITION" (PDF). Technical Report. ICG-TR-01/08. 

Source of the article : Wikipedia



EmoticonEmoticon

 

Start typing and press Enter to search