Combining partial parameter transfer strategy and spatial pyramid pooling for biological-cell classification

Zhen Yang; Xiuying He; Fan Yang; Zhijian Yin

doi:10.1117/12.2524453

6 May 2019 Combining partial parameter transfer strategy and spatial pyramid pooling for biological-cell classification

Zhen Yang, Xiuying He, Fan Yang, Zhijian Yin

Author Affiliations +

Proceedings Volume 11069, Tenth International Conference on Graphics and Image Processing (ICGIP 2018); 110691M (2019) https://doi.org/10.1117/12.2524453
Event: Tenth International Conference on Graphic and Image Processing (ICGIP 2018), 2018, Chengdu, China

Abstract

Predicting accurate location of Protein Subcellular is conductive to acknowledging the function of protein and finding the cancer biomarkers. Unfortunately, many experimental approaches for classifying the location of protein subcellular are still high-cost and time-consuming. However, deep convolutional neural network has achieved significant advances in many fields, such as image classification, object detection and segmentation, it’s driving us to use the deep convolutional neural network to classify the protein subcellular images. Because of unavoidable differences between bioimages and natural images, for instance, the biological subcellular image texture information is not as clear as natural images. That’s means if we use a deep model to train bio-images for finishing classification task directly, its result of this experiment will be not as good as what we expected. Therefore, we utilize Partial Parameter Transfer Strategy (PPTS) and Spatial Pyramid Pooling (SPP) algorithm for achieving bio-images classification task. Using the partial parameter transfer strategy to optimize the training process of the deep model is the first step, and the second procedure is to use spatial pyramid pooling layer to optimize the architecture of deep convolutional neural network. To solve the task of bioimages classification via jointly with the above two algorithms, the performance shows that our approach can acquire better results than traditional deep learning methods.

Citation Download Citation

Zhen Yang, Xiuying He, Fan Yang, and Zhijian Yin "Combining partial parameter transfer strategy and spatial pyramid pooling for biological-cell classification", Proc. SPIE 11069, Tenth International Conference on Graphics and Image Processing (ICGIP 2018), 110691M (6 May 2019); https://doi.org/10.1117/12.2524453

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Convolution

Proteins

Image classification

Neural networks

Convolutional neural networks

Data modeling

Image enhancement

Show All Keywords

Keywords/Phrases

Search In:

Publication Years