An Automatic Approach to Detect Girl Child Trafficking

Abstract

Girl child trafficking has become a matter of serious concern for human society. There are different manual approaches to stop and prevent it. However, these approaches need a huge amount of manual interventions. Consequently, there is a necessity to develop an automatic approach for detecting the incidents of girl child trafficking. In this work, we proposed a two-stage computational model for automatic girl child trafficking by analyzing images. Due to the unavailability of girl child trafficking images, we constructed a data set having one thousand four hundred ninety-six data. After careful observations, we decided to consider three features - age, emotion, and gender. Using these three features we developed our proposed computational model. In the first stage, the ResNet 50 deep neural network was used to determine the three feature values from an image. It was observed that these three models can perform the gender, age, and emotions with a testing accuracy of 80.23%, 76.29%, and 85.73%, respectively. In the next level, a Support Vector Machine (SVM) was used to determine whether there is a possibility of girl child trafficking or not. A K-fold cross-validation technique with K= 6 was used to avoid the overfitting problems. It has been observed our proposed model can detect girl child trafficking with an accuracy of 93.13%. The high accuracy observed in our study indicates the candidatures of our model for real-time child trafficking