An empirical study of handcrafted and dense feature extraction techniques for lung and colon cancer classification from histopathological images

•Implemented conventional handcrafted features extraction and transfer learning using pre-trained CNN networks as feature extractor for histopathological images of Lung and Colon cancer.•Classification of lung and colon cancer histopathological images (LC 25000 dataset) based on transfer learning and convention handcrafted features using conventional classifiers.•Comparative performance analysis of transfer learning approach and handcrafted features is presented.•RF classifier with features extracted by DenseNet-121 pre-trained network outperformed all other classifiers.