Convolutional Neural Network (CNN) is a recently used popular machine learning technique to classify images. However, choosing an optimum and efficient architecture is an inevitable challenge. The research goal was to implement CNN on face classification from low quality CCTV footage. The best model was gained from the hyperparameter optimization process used on CNN structure. The optimized hyperparameters were those connected to the structure network including activation function, the number of kernel, the size of kernel, and the number of nodes on the fully connected layers. Hyperparameter optimization strategy used was random grid coarse-to-fine search optimization approach. This approach combined random search, grid search, and coarse-to-fine technique that was easily and efficiently applied, yet worked well. Exhaustive-random search process was done by evaluating all selected activation functions and choosing another hyperparameters randomly. This was based on the assumption that activation functions were the most related hyperparameter to the model. The SELU activation function used in the next step was the one with the best average performance. Grid coarse-to-fine was conducted to optimize the number of kernel and the number of node on fully connected layer, while grid search was conducted to optimize the kernel size. This process aimed to locate optimal value gradually in hyperparameter which had high-dimensional space. Evaluation of the model resulted from the optimum hyperparameter was 97,56%.
Medical Image Processing, Human Face Classification, Face Recognition and Medical Imaging: Performance Evolution Histogram of Orientation Gradients
