A Review of Techniques for Image Classification to Enhance Online Animal Adoption Speed

Abstract

Overpopulation of stray dogs and cats is a serious threat to human community since they transmit a dangerous viral infection called rabies. Therefore overpopulation of strays needs to be controlled. Strategies to control overpopulation include sterilizing, euthanizing and adopting the strays. The ethical and popular method of acquisition in controlling strays is adoption. Adoptions are mostly carried out by animal shelters. The increase in usage of internet has provided platforms for shelters to advertise adoptions online by sharing pictures. Although there have been past researches on analyzing photo traits affecting the adoption speed, yet simpler improvements are required to guide shelters in posting influential photos. Hence it is essential to use an automated approach to guide shelters in posting influential photos to increase adoption speed. This paper presents the analysis of photo traits affecting adoption speed and computerized automated approaches of image classification. The classification approaches will be reviewed and used in designing an application of the ongoing research to predict the adoption speed of an input animal's image.