-
Recent Comments
Author Archives: joelgranados
Making sense of my software.
Today I needed a functionality that I was sure that I had already coded. Given that I have a bunch of active projects in different places in a semi-active status, I got a little confused and it took me some … Continue reading
The auto adjust exposure from ufraw.
The pictures I receive from the biologists are in raw format. This is good as it allows for tweaking before you put the picture in a more friendly format like jpeg or png. I’ve been using a really cool tool … Continue reading
Image segmentation based on pixel color: update.
I have continued to play with this and have increased the quality of my results. I have done some changes to the initial processing and I still need to experiment with lots of possibilities. Color space. I stuck with the … Continue reading
Image segmentation based on pixel color looks promising
Finally some expected results!!! Past Week(s): After consulting with some very talented computer vision professors, I decided to continue with Image segmentation based on pixel color. The idea is to segment the image based only on the value of a … Continue reading
Salix Arctica Albino Female
I have began to re-annotate (for the third time) the pictures from Zackenberg 2009. This time I am replacing the rectangles with polygons so I can better annotate the flower colors. In the process I came across a peculiar type … Continue reading
Posted in Uncategorized
Leave a comment
imroi: bloated Matlab commands
I was working with rbbox on my Matlab GUI application to create squares that marked important stuff inside an image. I recently needed to move away from the rectangle based approach to a polygon based approach. This meant not using rbbox. … Continue reading
Paper: A Universal and Robust Human Skin Color Model Using Neural Networks
The paper is interested in classifying pixels as skin/no-skin. They use YCbCr color space for their experiments. They analyse the behavior of this color space with respect to skin color. The found that the Y dimension does not have a … Continue reading
Don’t forget we are working with time series.
In the past weeks I have been looking at feature extraction methods like HOG, SIFT and SURF. These papers have given me great insight and some ideas. While I was reading these papers, I was always thinking to myself that … Continue reading
Posted in Uncategorized
Leave a comment
Better annotations -> Better PCA.
One of the issues that I identified in previous posts was that the original annotations were not of good quality. This included annotations that were incorrect and annotations that pointed to images that did not have enough differentiating information. I … Continue reading
Posted in annotation, PhD
Leave a comment
Paper: Digital Image Classification for Malaysian Blooming Flower
This paper has an impressive related work section. It describes work done in image processing related to segmentation and Neural Networks. From the context I believe that the paper only tries to detect one type of flower (The title also … Continue reading
Posted in papers, PhD
Leave a comment
Joel's Blog 