Currently In Beta
  • Categories


Page 1 of 1
ml

Author: Reasat Tahsin

As we have seen in the previuos notebook, there are some additional information in the label file of dataset-e. We are going to explore that in this notebook.
The digits from dataset **E** are extracted from the `BanglaLekha-Isolated` dataset which contains Bangla handwritten numerals, basic characters and compound characters.
The `BanglaLekha-Isolated` dataset was collected from Dhaka and Comilla. The age group of the subjects ranged from 6 years to 28 years with a high density between the ages of 16–20. Among the subjects, 59.4% were males while the remaining 40.6% were females.

Read More...
ml

Author: Reasat Tahsin

From our exploratory data analysis tutorials we have found that the digits in dataset A and B have unnecessary non digit areas. In this tutorial we are going to get a more focused crop of the digits. Functions from the opencv library will be very handy for this purpose.

Read More...
ml

Author: Reasat Tahsin

In this notebook, we are going to do some basic exploration of the dataset. We shall observe some samples from each dataset and number of image samples in them. As images are obtained from multiple sources, the quality of the segmentation and the dimension of the images varies a lot. We are going use data analysis toolkit pandas to perform our exploration. If you are not familiar with this library check out their 10 Minutes to pandas short introduction.

Read More...
Page 1 of 1