Season 3 Challenges

OPENED ON: 09 OCT 2017  |  CLOSED ON: 10 JAN 2018  |  REWARD: INR 3,00,000
Reward money is paid in exchange of legally acquiring the solution, implementing it to solve the problem and meeting the success criteria. Milestones for paying the reward money would depend upon the complexity of challenge and maturity of the proposed solution, which would be discussed with the solver as soon as the proposed solution is selected by us.

Short Description:

The wet blue leather needs to be segregated as per the intensity and size of tick marks on the surface. We are therefore inviting automated setup to identify these marks on wet blue leather surface.

Challenge Details

Wet blue leather sheets of size 4 to 8 sq. feet and thickness 6mm to 10mm are received at our facilities. These wet blue leather sheets consist of different defects which are classified into Anti-Mortem (defects like pin-holes, tick marks etc. caused by insect bites on animal skins) and Post-Mortem (defects produced due to disintegration of animal skins from fungus) which are inspected visually and segregated into different grades. These grades depend upon the percentage and type of defects on the leather surface. Leather surface containing more than 20?fects (by area) on its surface is considered as low grade. The size of the defects varies from 10 microns to 100 microns. We are looking for a solution which can help us identify these defects and segregate the wet blue leather into different grades, in an efficient manner. An automated process for identification, classification and segregation is desirable.

Currently, the defects are identified manually through naked eye in natural light. The leather is first spread over the table & it is then stretched by the operator to check for the defects. The defects are then identified manually by the operator and the leather segregated into low grade, medium grade or high grade categories. The process is very tedious as the defects are not easily visible through naked eyes even after stretching. Thus, the current process of identification of defects and segregation is very time consuming and not very efficient.

We have tried to improve the process by using different light sources (D65, UV, TL84), but were not very successful in making the defects visible easily.

We are looking for a solution which can help identification of defects easily, quantify the defects and segregate the leather subsequently. The solution should satisfy the following requirements;

  1. Easy identification of tick marks/pin holes.
  2. 100% segregation of wet blue leather based on the number and size of defects.
  3. Speed of processing should be faster than the current manual processing which takes less than a minute per wet blue leather.
  4. The solution should be environmental friendly.
  5. Should be cost effective.

Have any query or need more clarification about this challenge?