• State TI Thinks Resolved
  • Locked Locked
  • Replies 3 replies
  • Answers 1 answer
  • Subscribers 99 subscribers
  • Views 332 views
  • Users 0 members are here
Support feedback
Options
Options
Related

This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

How to obtain binary image

Jalwinder Singh
Intellectual 280 points
Other Parts Discussed in Thread: CCSTUDIO

Hi there.

I am tring to get binary image (not grayscale) for my face detection project on DM6437. Which thresholding (from IMGLIB) function or any other function can I use to  get binary image? Also which image format(grayscale or YcbCr) can be the input of such function for conversion?

 

Thanks'

Jalwinder

 

 

 

 

  • 0
    TI__Guru*** 125430 points

    IMGLIB functions are documented here.  Please read it and then ask a more specific question if you find any missing info.

  • 0 in reply to Brad Griffis
    Intellectual 280 points

    Thanks Brad for your reply.

    Actually I already have this PDF and I was using  IMG_thr_gt2max_8 function for converting an image to binary image. But this function was not working at all on my Video Preview example. One thing mentioned in this PDF is as follows:

    Different forms of image thresholding operations are used for various reasons in image/video processing
    systems. For example, one form of thresholding may be used to convert grayscale image data to binary
    image data for input to binary morphological processing.

    Taking this into consideration, I was using above mentioned library function. Was I using the right function?

    Please tell me which function will work to obtain binary image?

     

    Thanks

    Jalwinder

  • 0 in reply to Jalwinder Singh
    TI__Expert 8150 points

    Hello Jalwinder, Before chosing certain API from the IMGLIB, you need to clearly define few things:
    1. What is your input image format
    2. What is the processing you want to apply to the input data.
    3. What is the output you expect.

    The IMGLIB APIs are provided in source to reduce the SW development time by providing ready to use APIs or work as starting point for creating custom processing kernels. If you don't believe certain API is doing what it should, please include the source for that API in the pjt and single step to understand at what step the processing is going wrong. You can refer the source at C:\CCStudio_v3.3\c64plus\imglib_v201\kernels\

    In most cases, there is error in API usage. In some, API doesn't meet the requirement of the algorithm. In such cases, it is recommended that the user modifies the provided source to create the kernel that is really needed in the alg. Please study the doc and the provided source and suggest if you see any issue.
    Gagan