Object Classification by a Super-resolution Method and a Convolutional Neural Networks

Main Article Content

Bokyoon Na
Geoffrey Fox


Recently with many blurless or slightly blurred images, convolutional neural networks classify objects with around 90 percent classification rates, even if there are variable sized images. However, small object regions or cropping of images make object detection or classification difficult and decreases the detection rates. In many methods related to convolutional neural network (CNN), Bilinear or Bicubic algorithms are popularly used to interpolate region of interests. To overcome the limitations of these algorithms, we introduce a superresolution method applied to the cropped regions or candidates, and this leads to improve recognition rates for object detection and classification. Large object candidates comparable in size of the full image have good results for object detections using many popular conventional methods. However, for smaller region candidates, using our super-resolution preprocessing and region candidates, allows a CNN to outperform conventional methods in the number of detected objects when tested on the VOC2007 and MSO datasets.

Article Details