IMAGE RECOGNITION STEPS

NIMISHA.T13MCA11030

IMAGE RECOGNITION STEPS

FORMATTING

Capturing an image from a camera and bringing it into a digital form.

Digital representation of an image in the form of pixels

OBSERVED IMAGE

CONDITIONING

In an image, there are features which are uninteresting, either because they were introduced into the image during

the digitization process as noise, or because they form part of a background.

An observed image is composed of informative patterns modified by uninteresting random variations. Conditioning suppresses, or normalizes, the uninteresting

variations in the image, effectively highlighting the interesting parts of the image.

Applied uniformly and in context-independent.

LABELING

Informative patterns in an image have structure. Patterns are usually composed of adjacent pixels which share some property such that it can be inferred that they are part of the same structure (e.g., an edge). Edge detection techniques focus on identifying continuous adjacent pixels which differ greatly in intensity or color, because these are likely to mark boundaries, between objects, or an object and the background, and hence form an edge.

LABELING (CONTINUE…)

An edge is said to occur at a point in the image if some image attribute changes in value discontinuously at that point. Examples are intensity edges. An ideal edge, in one dimension, may be viewed as a step change in intensity;

LABELING (CONTINUE…)

One-dimensional edge

LABELING (CONTINUE…)

Edge detected image:

LABELING (CONTINUE…)

If the step is detected, the high-valued and low-valued pixels are labeled as part of an edge.

After the edge detection process is complete, many edge will have been identified. However, not all of the edges are significant.

Thesholding filters out insignificant edges. The remaining edges are labeled. More complex labeling operations may involve identifying and labeling shape primitives and corner finding

LABELING (CONTINUE…)

Thresholding the image:

GROUPING

Grouping can turn edges into lines by determining that different edges belong to the same spatial event.

A grouping operation, where edges are grouped into lines, is called line-fitting.

The first 3 operations represent the image as a digital image data structure (pixel information), however, from the grouping operation the data structure needs also to record the spatial events to which each pixel belongs.

This information is stored in a logical data structure.

GROUPING (CONTINUE…)

Line-fitting of the image:

EXTRACTING

Grouping only records the spatial event(s) to which pixels belong. Feature extraction involves generating a list of properties for each set of pixels in a spatial event.

These may include a set's centroid, area, etc. Additionally properties depend on whether the group is considered a region or an arc. If it is a region, then the number of holes might be useful. In the case of an arc, the average curvature of the arc might be useful to know

Feature extraction can also describe the topographical relationships between different groups. Do they touch? Does one occlude another? Where are they in relation to each other? etc.

MATCHING

Finally, once the pixels in the image have been grouped into objects and the relationship between the different objects has been determined, the final step is to recognize the objects in the image.

Once an object or set of object parts has been recognized, measurements (such as the distance between two parts, the angle between two lines or the area of an object part) can be made.

Matching involves comparing each object in the image with previously stored models and determining the best match template matching.

Example:

IMAGE TRANSMISSION

Transmission of digital images through computer networks There are several requirements on the networks when

images are transmitted:1. The network must accommodate bursty data transport

because image transmission is bursty(high-bandwidth transmission over a short period)

2. Image transmission requires reliable transport3. Time-dependence is not a dominant characteristic of the

image in contrast to audio/video transmission.

IMAGE TRANSMISSION(CONTINUE…)

Image size depends on the image representation format used for transmission.

Formats: Raw Digital Image data transmission Compressed image data transmission Symbolic image data transmission

IMAGE TRANSMISSION(CONTINUE…)

Raw image data transmission In this case, the image is generated through a video

digitizer and transmitted in its digital format. The size can be computed in the following manner:

size = spatial-resolution x pixel-quantization Eg: The transmission of an image with a resolution of 640 x

480 pixels and pixel quantization of 8 bits per pixel requires transmission of 307,200 bytes through the network.

IMAGE TRANSMISSION(CONTINUE…)

Compressed image data transmission : In this case, the image is generated through a video

digitizer and compressed before transmission.

Methods such as JPEG or MPEG, are used to downsize the image.

The reduction of image size depends on the compression method and compression rate.

IMAGE TRANSMISSION(CONTINUE…)

Symbolic image data transmission : The image is represented through symbolic data

representation as image primitives (e.g..2D or 3D geometric representation), attributes and other control information.

This image representation method is used in computer graphics.

Image size is equal to the structure size, which carries the transmitted symbolic information of the image.

THANK YOU