Today there is a massive attempt to exclude the same object from different images. Today there is a massive attempt to exclude the same object from different images

Today there is a massive attempt to exclude the same object from different images.

• Today there is a massive attempt to exclude the same object from different images.

• Such problem is not an easy task as it seems , furthermore the algorithm which is presented today is not 100% accurate even though it is efficient.

An Efficient Algorithm for Co-segmentation .

• An Efficient Algorithm for Co-segmentation .

• Clothing Co-segmentation for Recognizing People .

• iCoseg: Interactive Co-segmentation on your iOS device (in short).

• Implementation of Co-segmentation in MATLAB + C++ Code.

The Goal of the Algorithm:

• The Goal of the Algorithm:

• Given a set of images , we need to detect the same foreground in the set of images despite the differences in the background.

• Approach :

• We will reward consistency in the two foreground histograms.

Co-segmentation settings.

• Co-segmentation settings.

• Similarity weight.

• Foreground and background pixels.

• “MRF penalties”.

The segmentation of each image will partition the set of pixel into foreground versus background pixels.

• The segmentation of each image will partition the set of pixel into foreground versus background pixels.

• Our goal is to ensure that the foreground in the two images are similar.

The MRF formulation of one image is then :

• The MRF formulation of one image is then :

Therefore the formulation of co-segmentation problem is then a linear combination of MRF minimization and similarity maximization:

• Therefore the formulation of co-segmentation problem is then a linear combination of MRF minimization and similarity maximization:

We have seen an efficient algorithm, running in polynomial time (the running time of a max-flow algorithm).

• We have seen an efficient algorithm, running in polynomial time (the running time of a max-flow algorithm).

The goal:

• The goal:

• Given a four consumer image collection , we need to recognize individuals among these image collection.

• Approach:

• Using the clothing data.

Graph Cut.

• Graph Cut.

• Normalized Cut.

• Texture feature vector.

What are Graph-Cuts ?

• What are Graph-Cuts ?

• Set of edges whose removal makes a graph disconnected.
• It’s the partition of V into A,B such that and

• A graph can be partitioned into two disjoint sets ,we define the partition cost as:

• The bipartition of the graph which minimizes the cut value is called the Min-Cut .

Cut(A,B) is sum of weights with one end in A and one end in B ,we want to minimize the cut cost.

• Cut(A,B) is sum of weights with one end in A and one end in B ,we want to minimize the cut cost.

• Assoc(A,V) is sum of all edges with one end in A , we want to maximize the sum of all weights for every A,B element in the partition

Feature vector based on texture segmentation:

• Feature vector based on texture segmentation:

• We can use spatial filter for where the DOOG filters at various scales and orientations .

The color encoding system used for analog television worldwide (NTSC, PAL and SECAM). The YUV color space (color model) differs from RGB, which is what the camera captures and what humans view. 

• The color encoding system used for analog television worldwide (NTSC, PAL and SECAM). The YUV color space (color model) differs from RGB, which is what the camera captures and what humans view. 

• The Y in YUV stands for "luma," which is brightness.

• U and V provide color information and are "color difference" signals of blue minus luma (B-Y) and red minus luma (R-Y)

RGB to LCC / YUV :

• RGB to LCC / YUV :

Features are extracted from the faces and clothing of people:

• Features are extracted from the faces and clothing of people:

• Face features:
• Are extracted using an algorithm of detecting face which also can estimate the position of the eyes.
• Each face is normalized in scale (49*61 pixels) and projected onto a set of Fisherfaces , representing each face as a 37-dimentional vector.

2:

• 2:
• The 5-dimentional vector at each pixel is quantized to the index of the closest visual word , so each pixel in the region is associated with a word in the dictionary (or several words) then all the words of all the pixels in the region are counted in a histogram.
• The Histogram per region is the "feature" of the region. The visual word clothing features are represented as v.

The same day mutual information maps are reflected (symmetry is assumed) , summed and thresholded (by a value constant across image collection) to yield clothing masks that appear remarkably similar across collections.

• The same day mutual information maps are reflected (symmetry is assumed) , summed and thresholded (by a value constant across image collection) to yield clothing masks that appear remarkably similar across collections.

Better Clothing Recognition Improves Recognition:

• Better Clothing Recognition Improves Recognition:

• We use nine nearest neighbors and repeat random labeling procedure 50 times to the average performance.

The identity recognition and clothing segmentation problems are inter-twined; a good solution for one aides in the solution for the other.

• The identity recognition and clothing segmentation problems are inter-twined; a good solution for one aides in the solution for the other.

• Multiple images of the same person improves clothing segmentation.

• Person recognition improves with improvements to the clothing segmentation.

Dorit S. Hochbaum, Vikas Singh. An efficient algorithm for co-segmentation. ICCV Oct 2009 , Kyoto, Japan, the 12th IEEE Conference on Computer Vision. 

• Dorit S. Hochbaum, Vikas Singh. An efficient algorithm for co-segmentation. ICCV Oct 2009 , Kyoto, Japan, the 12th IEEE Conference on Computer Vision. 

• A. C. Gallagher and T. Chen. Clothing cosegmentation for recognizing people. In Proc. of Conf. on Computer Vision and Pattern Recognition, 2008.

• Slides Credit: Jad Silbak

• http://en.wikipedia.org/wiki/YUV

• http://chenlab.ece.cornell.edu/people/jasonlew/Poster_JasonLew.pdf