Robo-advisors to predict switching of jobs using space in handwriting image

Abstract

Predicting switching of jobs has been in quest for several years. The study starts with collection of manually written text specimen in A4 sheet. At the beginning gray scale or color copy is extracted by the robo-advisor and more shielding executed to transform to binary image. For identifying the gaps amidst characters Skew-normalization is used in the manuscript after segmentation. After that a comparison is computed with space mean among closed loops created by characters and word spaces to identify character. The characters are then matched with the requirements of job. Accordingly, the new appraisal is compared against the already existing. If the performance degrades, switching is predicted along with the possible job options. The main agenda of the document is to analyze switching jobs on the basis of behavior from gaps in manually written manuscripts. The recommended approach is approved with 600 samples of IAM database with diverse authors having various culture. The analysis concludes the recommended method attains 64% and above level of efficiency.