Research On Singleframe Superresolution Reconstruction Algorithm For Low Resolution Cell Images Based On Convolutional Neural Network

• doi: 10.1109/ICIVC.2018.8492913
• title: Research on Single-Frame Super-Resolution Reconstruction Algorithm for Low Resolution Cell Images Based on Convolutional Neural Network
• publisher: IEEE
• isbn: 978-1-5386-4992-3
• issn:
• rank: 3458
• access_type: LOCKED
• content_type: Conferences
• abstract: Aiming at the problem of low resolution and low amount of contented of cell images collected by lens-less cell detection systems consisting of CMOS image sensors and microfluidic channels, a novel CSRNet (Cell Super Resolution Network) reconstruction network for lens-less cell detection systems is proposed in this paper. First, the images of cells on blood smears were collected with a microscope (MshOt model), and using a threshold segmentation algorithm to divide it to 80×80 high-resolution (HR) reference image for training. After segmentation, the HR cell image is downsampled by the bicubic downsampling algorithm to obtain a 20×20 low resolution (LR) cell image. Training the CSRNet reconstruction network with a training set consisting of HR and LR cell images. Then the cell image which was collected by the lens-less cell detection systems is segmented. The segmented cell image is inputed into a trained network model, and a high-resolution cell image with more detailed information is as a output. The experimental results show that the effect of the proposed CSRNet network reconstruction is better than both the bicubic interpolation reconstruction and the FSRCNN reconstruction in terms of subjective visual and objective evaluation indicators. Therefore, the CSRNet network can be used to improve the image resolution which collected by lens-less cell detection systems.
• article_number: 8492913
• pdf_url: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8492913
• html_url: https://ieeexplore.ieee.org/document/8492913/
• abstract_url: https://ieeexplore.ieee.org/document/8492913/
• publication_title: 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC)
• conference_location: Chongqing, China
• conference_dates: 27-29 June 2018
• publication_number: 8476690
• is_number: 8492718
• publication_year: 2018
• publication_date: 27-29 June 2018
• start_page: 369
• end_page: 373
• citing_paper_count: 2
• citing_patent_count: 0
• download_count: 154
• insert_date: 20181018
• index_terms:
  • ieee_terms:
    • Conferences
    • Handheld computers
  • author_terms:
    • Iensless
    • CSRNet network
    • resolution
  • dynamic_index_terms:
    • Low Resolution
    • Convolutional Neural Network
    • Cell Imaging
    • Reconstruction Algorithm
    • Super-resolution Reconstruction
    • Super-resolution Reconstruction Algorithm
    • Super Resolution Reconstruction Algorithm
    • Single-frame Super-resolution
    • Single-frame Super Resolution
    • High-resolution Images
    • Blood Smears
    • Blood Films
    • Reference Image
    • Image Sensor
    • Camera Sensor
    • Bicubic Interpolation
    • Trained Network Model
    • Blood Cells
    • Red Blood Cells
    • Erythrocytes
    • Erythroid
    • Learning Rate
    • Convolutional Layers
    • Output Layer
    • Image Information
    • Convolution Operation
    • Low-resolution Images
    • Super-resolution Algorithms
    • Deconvolutional Layers
    • Image Block
    • Convolutional Neural Network Structure
    • Reconstruction Method
    • Reconstruction Methods
    • Reconstruction Results
    • Human Eye
    • Human Eyes
    • Red Images
    • Convolution Kernel
• isbn_formats:
  • format: Print on Demand(PoD) ISBN, value: 978-1-5386-4992-3, isbnType: New-2005
  • format: CD, value: 978-1-5386-4990-9, isbnType: New-2005
  • format: Electronic ISBN, value: 978-1-5386-4991-6, isbnType: New-2005
• authors:
  • Author Name: Xiang Ma
    Affiliation: Department of Electronic Engineering, Xi'an University of Technology, Xi'an, China
    Author URL: https://ieeexplore.ieee.org/author/37086485534
    ID: 37086485534
    Order: 1
    Author Affiliations:
    • Department of Electronic Engineering, Xi'an University of Technology, Xi'an, China
  • Author Name: Ningmei Yu
    Affiliation: Department of Electronic Engineering, Xi'an University of Technology, Xi'an, China
    Author URL: https://ieeexplore.ieee.org/author/37588111700
    ID: 37588111700
    Order: 2
    Author Affiliations:
    • Department of Electronic Engineering, Xi'an University of Technology, Xi'an, China
  • Author Name: Yuan Fang
    Affiliation: Department of Electronic Engineering, Xi'an University of Technology, Xi'an, China
    Author URL: https://ieeexplore.ieee.org/author/37085401865
    ID: 37085401865
    Order: 3
    Author Affiliations:
    • Department of Electronic Engineering, Xi'an University of Technology, Xi'an, China
  • Author Name: Dongfang Wang
    Affiliation: Department of Electronic Engineering, Xi'an University of Technology, Xi'an, China
    Author URL: https://ieeexplore.ieee.org/author/37675959400
    ID: 37675959400
    Order: 4
    Author Affiliations:
    • Department of Electronic Engineering, Xi'an University of Technology, Xi'an, China

Image Sensor

• sensor_type: CMOS
• resolution: extracted data not available
• dynamic_range: extracted data not available
• pixel_size: extracted data not available
• dark_current: extracted data not available

Optical Data

• focal_length: extracted data not available
• aperture: extracted data not available
• field_of_view: extracted data not available
• distortion: extracted data not available

Performance Metrics

• frame_rate: extracted data not available
• signal_to_noise_ratio: extracted data not available
• sensitivity: extracted data not available
• shutter_speed: extracted data not available
• power_consumption: extracted data not available
• noise: extracted data not available

Applications & Benefits

• cell_imaging: CMOS image sensors are used in smartphones, medical devices, and automotive systems.
• benefits: Excels in conversion of light into electrical signals enabling digital imaging.

Supporting Organizations

• supported_by: extracted data not available

Manuscript Details

• publication_date: 27-29 June 2018

Relevancy Score

• score: 10
• missing_fields:
  • resolution
  • dynamic_range
  • pixel_size
  • dark_current
  • focal_length
  • aperture
  • field_of_view
  • distortion
  • frame_rate
  • signal_to_noise_ratio
  • sensitivity
  • shutter_speed
  • power_consumption
  • noise
  • supported_by
  • authors
  • publication_date

Processed JSON Filename

request_357747aa-e0fb-4ca2-b789-231ade79f21d-research_on_singleframe_superresolution_reconstruction_algorithm_for_low_resolution_cell_images_based_on_convolutional_neural_network.json