3.4 Processing
About1 Introduction2 Image Recognition3 TransApplet4 API5 Interface6 Input7 Image Display8 Preprocessing9 Processing10 Normalization11 Parameter Class12 Image Signatures13 Unsupervised Filters14 BioFilters15 NeuralFilters16 Dynamic Library17 NeuralNet Filter18 Parameters19 Input Options20 Database Input21 Video Input22  Live Video Input23  Counting & Tracking24  Counting 25  Batch Job26 ImageFinder for DOS27 ImageHunt 28 Support Packages

3.1 API 
3.2 Input 
3.3 Display 
3.4 Processing 
3.5 Parameters 
3.6 Signature 
3.7 Dynamic Library 
3.8 Segment Matching 
3.9 Input 
3.10 Counting 
3.11 Batch 
3.12 Customization 
[Home][3 TransApplet][3.4 Processing]


3.4   Image Preprocessing, Processing, & Normalization

Chapter 8, Image Preprocessing, and Chapter 9, Image Processing, briefly describes the image preprocessing and image processing required for the ImageFinder.

The Image Preprocessing sub-layer prepares the image for the ImageFinder. Image Preprocessing is not unique; there are many options available. Some are better than others.

The Image Preprocessing Layer consists of one filter, the Preprocessing filter.

The Image Processing Layer consists of three types of filters:

    Edge Filters (Optional);

    Threshold Filters (Required); and

    Clean-Up Filters (Optional).

The ImageFinder applies these three filters in the above order.

  •    The Edge Filters attempt to exaggerate the main features a user is looking for.
  •    The Threshold Filters attempt to suppress the background.
  •    The Clean-Up Filters will smooth the resulting image to reduce recognition error.

From the user’s point of view, Image Processing means you have to set three filters: Edge Filters, Threshold Filters, and Clean-Up Filters. The Threshold Filter is required; the other two filters are optional. This chapter will introduce the class library, “Attrasoft.transapplet70.ImageProcessing70”.

Chapter 10, Normalization, briefly describes the Normalization process required for the ImageFinder. At the end of the Image Processing, the original image is transformed into a new image with the main features exaggerated and the background suppressed, i.e. the result is still an image. The underlying image matching engine will process data in a particular format, therefore, an image will need to be formatted for the internal matching engine via a normalization process.

Normalization has 1 filter, Reduction Filter, which will prepare the images for the underlying image matching engine. The Attrasoft Image Matching Engine is an internally developed algorithm, which is called the “Attrasoft Boltzmann Machine” or ABM. The ABM neural net deployed in the ImageFinder, by default, is a 100x100 array of neurons.

While any size of ABM neural net can be used, when coming to a particular application, a decision has to be made. The ImageFinder uses 6 different sizes:

  •    10,000 neurons,
  •    8,100 neurons,
  •    6,400 neurons,
  •    4,900 neurons, or
  •    2,500 neurons.


[Home][About][1 Introduction][2 Image Recognition][3 TransApplet][4 API][5 Interface][6 Input][7 Image Display][8 Preprocessing][9 Processing][10 Normalization][11 Parameter Class][12 Image Signatures][13 Unsupervised Filters][14 BioFilters][15 NeuralFilters][16 Dynamic Library][17 NeuralNet Filter][18 Parameters][19 Input Options][20 Database Input][21 Video Input][22 Live Video Input][23 Counting & Tracking][24 Counting ][25 Batch Job][26 ImageFinder for DOS][27 ImageHunt ][28 Support Packages]

Copyright (c) 2006 - 2007 Attrasoft. All rights reserved.