ANPR Day 20: ANN - Challenges

By -
The major challenge in training ANN is the large dataset required to get more accurate results. More and more unique images are required  for each character. Also all of these images should be normalized and have same size,i.e., 10 x 10 pixels. To get this dataset we have to use the segmented characters produced by SVM - the Ouroboro problem. No clear solution to this problem has been found. 

Comments

Post a Comment

Popular posts from this blog

Project Wild Penguin 22.4.2017: To delete directories inside current directory whose contents are less than a given size

By -
With GNU find and GNU coreutils, and assuming your directories don't have newlines in their names: find . -mindepth 1 -maxdepth 1 -type d -exec du -ks {} + | awk '$1 <= 50' | cut -f 2- This will list directories with total contents smaller than 50K. If you're happy with the results and you want to delete them, add | xargs -d \\n rm -rf to the end of the command line. Command: find . -mindepth 1 -maxdepth 1 -type d -exec du -ks {} + | awk '$1 <= 50' | cut -f 2- | xargs -d \\n rm -rf Source:  https://unix.stackexchange.com/questions/214089/command-to-delete-directories-whose-contents-are-less-than-a-given-size
Read more

ANPR Day 6: Existing Systems

By -
Today, the existing systems were to be studied. But it was found that the existing system for number plate recognition is still basically in pre-technological era. Most of the recognition work is done manually because of which the whole process is long, tedious and lacks any transparency. It is unable to take benefits of the present and future technological capabilities. Due to which most of the traffic and security applications are done through outdated or pedestrian methods which are slow, error-prone and impractical in current scenario. With the advent of information technologies, it has become an increasing necessity that all existing systems be upgraded and integrated with this new technology in order to make these systems more advanced, transparent, fast and better than before. Another motivation for this project was the heinous crime that was committed on 16 December, 2012 in Delhi. In which the 23 year old woman was brutally gang-raped in a moving bus. That bus did not h...
Read more

Python Chronicles: Updating FB Status using Python & GraphAPI

By -
So, while I was exploring the infinite possibilities presented by Python. I found this great python package facepy . Using which you can update your facebook status from python terminal. The only prerequisite is that you must be facebook developer to gain access to GraphAPI. Following the steps given below, you can also update your status using python: 1. Download facepy and install it by running this command:       python setup install 2. Create a new application or use an existing one previously created. 3. Run python.exe from command terminal (cmd in Windows). Use the user access token created in the previous step with facepy: >> from facepy import GraphAPI >>ACCESS_TOKEN = 'access-token-copied-from-graph-api-explorer-on-web-browser' >>graph = GraphAPI(ACCESS_TOKEN) >>graph.post('me/feed', message='Hello World!') That's it. You may further experiment with GraphAPI using facepy. Happy Experimenting!! MG
Read more