Monday
The limitations we faced in our project at this point pushed us to rely on another resort to using the text on the IC’s for our matching. The IC’s, in general, have a lot of constraints; the numerous pins on the side of every IC’s hindered our progress when we tried using SIFT and FLANN. Because of the constraints that computer vision offers, we had to speak with Professor Crandall on another approach to our problem.

Tuesday
Professor Crandall, on Tuesday during our lab meeting, recommended us to try Google’s Cloud Vision API and compare its results to Tesseract, another Optical Character Recognition platform. He told us that because the ICs have given us a lot of trouble and visual comparison seemed difficult with them, we should try matching by just using the text on the ICs. Although this sounded simple at first glance, the small size and fade of the texts on the ICs proved to be a limitation. Google’s OCR did a great job reading the text (roughly 85% accurate), whilst Tesseract did a horrible job reading the text on the ICs. Nonetheless, Professor Crandall wants us to continue experimenting with both OCR applications so we can include the results in our poster.

Wednesday
During the week, Professor Crandall gave us the opportunity to visit the Cyberinfrastructure building which control’s all of IU Bloomington’s network traffic and web services. The tour was very interesting; we got the chance to see state of the art computing types of equipment, including supercomputers, and many more.

Thursday

Brainstorming.

Friday
With barely two weeks left, Gerald and I started brainstorming what to include in our poster. Since we did not really complete much of our project, we plan on showing what we have been working on and where we got stuck at. Although our project was not complete, we learned a lot these past eight weeks, and our insight into computer science and research has massively broadened.