Essays about: "Computer vision"

Showing result 1 - 5 of 358 essays containing the words Computer vision.

  1. 1. A Digits-Recognition Convolutional Neural Network on FPGA

    University essay from Linköpings universitet/Datorteknik

    Author : Zhenyu Wang; [2019]
    Keywords : ;

    Abstract : A convolutional neural network (CNN) is a deep learning framework that is widely used in computer vision. A CNN extracts important features of input images by perform- ing convolution and reduces the parameters in the network by applying pooling operation. READ MORE

  2. 2. Active Stereo Reconstruction using Deep Learning

    University essay from Linköpings universitet/Institutionen för medicinsk teknik

    Author : Helena Kihlström; [2019]
    Keywords : Computer Vision; Deep Learning; Stereo Reconstruction;

    Abstract : Depth estimation using stereo images is an important task in many computer vision applications. A stereo camera contains two image sensors that observe the scene from slightly different viewpoints, making it possible to find the depth of the scene. An active stereo camera also uses a laser projector that projects a pattern into the scene. READ MORE

  3. 3. Developing vision substitution products using computer vision

    University essay from Lunds universitet/Ergonomi och aerosolteknologi

    Author : Björn Gummesson; [2019]
    Keywords : product development; user centered design; interaction design; rehabilitation engineering; Technology and Engineering;

    Abstract : The purpose of this thesis is two-fold. The first is to investigate if cutting edge technology can be used to enhance the life for people with visual impairments. The second is to provide a simple example of how the design process can look from the beginning to a finished Hi-Fi prototype. READ MORE

  4. 4. Normalized Convolution Network and Dataset Generation for Refining Stereo Disparity Maps

    University essay from Linköpings universitet/Datorseende; Linköpings universitet/Datorseende

    Author : Daniel Cranston; Filip Skarfelt; [2019]
    Keywords : Disparity Map; Disparity Refinement; Dataset Generation; Neural Network; Normalized Convolution;

    Abstract : Finding disparity maps between stereo images is a well studied topic within computer vision. While both classical and machine learning approaches exist in the literature, they frequently struggle to correctly solve the disparity in regions with low texture, sharp edges or occlusions. READ MORE

  5. 5. Image enhancement effect on the performance of convolutional neural networks

    University essay from Blekinge Tekniska Högskola/Institutionen för datavetenskap

    Author : Xiaoran Chen; [2019]
    Keywords : Image Enhancement; Convolutional Neural Networks; Deep Learning; Transfer Learning;

    Abstract : Context. Image enhancement algorithms can be used to enhance the visual effects of images in the field of human vision. So can image enhancement algorithms be used in the field of computer vision? The convolutional neural network, as the most powerful image classifier at present, has excellent performance in the field of image recognition. READ MORE