A Multi-Stage Framework for Classification of Unconstrained Image Data From Mobile Phones

2018 ◽  
pp. 2387-2401
Author(s):  
Shashank Mujumdar ◽  
Dror Porat ◽  
Nithya Rajamani ◽  
L.V. Subramaniam
Keyword(s):  
Image Classification ◽  
Mobile Phones ◽  
Real World ◽  
Image Data ◽  
Complex Environments ◽  
Second Stage ◽  
Classification Framework ◽  
Multi Stage ◽  
Efficient Detection

During the past decade, the number of mobile electronic devices equipped with cameras has increased dramatically and so has the number of real-world applications for image classification. In many of these applications, the image data is captured in an uncontrolled manner and in complex environments and conditions under which existing image classification techniques may not perform well. In this paper, the authors provide a detailed description of an efficient multi-stage image classification framework that is robust enough to remain effective also under challenging imaging conditions, and demonstrate its effectiveness in the context of classification of real-world images of dumpsters captured by mobile phones in the metropolitan city of Hyderabad. Their system is able to achieve accurate classification of the cleanliness state of the dumpsters by utilizing a multi-stage approach, where the first stage is the efficient detection of the dumpster and the second stage is the classification of its state. The authors provide a detailed analysis of the performance of the system as well as comprehensive experimental results on real-world image data.

A Multi-Stage Framework for Classification of Unconstrained Image Data from Mobile Phones

2014 ◽  
Vol 5 (4) ◽  
pp. 22-35
Author(s):  
Shashank Mujumdar ◽  
Dror Porat ◽  
Nithya Rajamani ◽  
L.V. Subramaniam
Keyword(s):  
Image Classification ◽  
Mobile Phones ◽  
Real World ◽  
Image Data ◽  
Complex Environments ◽  
Classification Framework ◽  
Multi Stage ◽  
Efficient Detection ◽  
World Image

During the past decade, the number of mobile electronic devices equipped with cameras has increased dramatically and so has the number of real-world applications for image classification. In many of these applications, the image data is captured in an uncontrolled manner and in complex environments and conditions under which existing image classification techniques may not perform well. In this paper, the authors provide a detailed description of an efficient multi-stage image classification framework that is robust enough to remain effective also under challenging imaging conditions, and demonstrate its effectiveness in the context of classification of real-world images of dumpsters captured by mobile phones in the metropolitan city of Hyderabad. Their system is able to achieve accurate classification of the cleanliness state of the dumpsters by utilizing a multi-stage approach, where the first stage is the efficient detection of the dumpster and the second stage is the classification of its state. The authors provide a detailed analysis of the performance of the system as well as comprehensive experimental results on real-world image data.

Classification of Visual Cortex Cells with the Use of a New Neural Network Model

Perception ◽  
1997 ◽  
Vol 26 (1_suppl) ◽  
pp. 108-108
Author(s):  
V N Chihman ◽  
S V Mironov ◽  
F N Makarov ◽  
K N Dudkin
Keyword(s):  
Visual Cortex ◽  
Cortical Neurons ◽  
Feature Vector ◽  
Image Data ◽  
Recognition Process ◽  
Second Stage ◽  
Primary Image ◽  
Image Descriptions ◽  
Interactive Algorithms

To identify the intrinsic connections within different layers of area 17 of the cat visual cortex we studied the initial neurons labelled by horseradish peroxidase retrograde axonal transport in serial sections. A computer model of visual neural networks (Dudkin et al, 1995 Proceedings of SPIE 122) has been specially developed in these studies to classify cortical neurons according to their specific anatomic features. There are two main stages of the recognition process in this model: feature selection by nonlinear neural operators and classification (clustering) connected with algorithms of cluster analysis. In the first stage, the primary image processing and segmentation are performed by interactive algorithms, which allow us to form several primary image descriptions and to extract the basic description elements of the cell. From these elements, a feature vector consisting of 17 normalised measures is extracted. In the second stage of the recognition process several algorithms are used to cluster the cells according to the feature vectors extracted. It was possible to group these vectors into compact clusters and to associate each group of vectors with a certain type of cells (pyramidal, spiny, and smooth stellate cells). These results are part of the task of creating a computer image data base and 3-D reconstruction of the cortico-cortical connections in the visual system.

scholarly journals Pathomics and Deep Learning Classification of a Heterogeneous Fluorescence Histology Image Dataset

2021 ◽  
Vol 11 (9) ◽  
pp. 3796
Author(s):  
Georgios S. Ioannidis ◽  
Eleftherios Trivizakis ◽  
Ioannis Metzakis ◽  
Stilianos Papagiannakis ◽  
Eleni Lagoudaki ◽  
...  
Keyword(s):  
Image Classification ◽  
Image Acquisition ◽  
Image Data ◽  
Pooled Data ◽  
Support Tools ◽  
Image Dataset ◽  
Feature Based ◽  
Good Differentiation ◽  
Pathology Image

Automated pathology image classification through modern machine learning (ML) techniques in quantitative microscopy is an emerging AI application area aiming to alleviate the increased workload of pathologists and improve diagnostic accuracy and consistency. However, there are very few efforts focusing on fluorescence histology image data, which is a challenging task, not least due to the variable imaging acquisition parameters in pooled data, which can diminish the performance of ML-based decision support tools. To this end, this study introduces a harmonization preprocessing protocol for image classification within a heterogeneous fluorescence dataset in terms of image acquisition parameters and presents two state-of-the-art feature-based approaches for differentiating three classes of nuclei labelled by an expert based on (a) pathomics analysis scoring an accuracy (ACC) up to 0.957 ± 0.105, and, (b) transfer learning model exhibiting ACC up-to 0.951 ± 0.05. The proposed analysis pipelines offer good differentiation performance in the examined fluorescence histology image dataset despite the heterogeneity due to the lack of a standardized image acquisition protocol.

scholarly journals An Innovative Intelligent System with Integrated CNN and SVM: Considering Various Crops through Hyperspectral Image Data

2021 ◽  
Vol 10 (4) ◽  
pp. 242
Author(s):  
Shiuan Wan ◽  
Mei Ling Yeh ◽  
Hong Lin Ma
Keyword(s):  
Neural Network ◽  
Support Vector Machine ◽  
Image Classification ◽  
Hyperspectral Image ◽  
Intelligent System ◽  
Image Data ◽  
Support Vector ◽  
Hyperspectral Image Classification ◽  
Hyperspectral Image Data

Generation of a thematic map is important for scientists and agriculture engineers in analyzing different crops in a given field. Remote sensing data are well-accepted for image classification on a vast area of crop investigation. However, most of the research has currently focused on the classification of pixel-based image data for analysis. The study was carried out to develop a multi-category crop hyperspectral image classification system to identify the major crops in the Chiayi Golden Corridor. The hyperspectral image data from CASI (Compact Airborne Spectrographic Imager) were used as the experimental data in this study. A two-stage classification was designed to display the performance of the image classification. More specifically, the study used a multi-class classification by support vector machine (SVM) + convolutional neural network (CNN) for image classification analysis. SVM is a supervised learning model that analyzes data used for classification. CNN is a class of deep neural networks that is applied to analyzing visual imagery. The image classification comparison was made among four crops (paddy rice, potatoes, cabbages, and peanuts), roads, and structures for classification. In the first stage, the support vector machine handled the hyperspectral image classification through pixel-based analysis. Then, the convolution neural network improved the classification of image details through various blocks (cells) of segmentation in the second stage. A series of discussion and analyses of the results are presented. The repair module was also designed to link the usage of CNN and SVM to remove the classification errors.

P-MART: Towards a classification of online prediction markets

First Monday ◽  
2011 ◽  
Author(s):  
Dorit Geifman ◽  
Daphne Ruth Raban ◽  
Rafaeli Sheizaf
Keyword(s):  
Real World ◽  
Social Computing ◽  
Market Price ◽  
Prediction Markets ◽  
Current State ◽  
Classification Framework ◽  
Online Prediction ◽  
Facet Classification ◽  
Considerable Complexity

Prediction Markets are a family of Internet–based social computing applications, which use market price to aggregate and reveal information and opinion from dispersed audiences. The considerable complexity of these markets inhibited the full realization of the promise so far. This paper offers the P–MART classification as a tool for organizing the current state of knowledge, aiding the construction of tailored markets, identifying ingredients for Prediction Markets’ success and encouraging research. P–MART is a dual–facet classification of implementations of Prediction Markets describing traders and markets. The proposed classification framework was calibrated by examining a variety of real–world online implementations. A publicly accessible wiki resource accompanies this paper in order to stimulate further research and future expansion of the classification.

scholarly journals A New Approach of Ensemble Learning Technique to Resolve the Uncertainties of Paddy Area through Image Classification

2020 ◽  
Vol 12 (21) ◽  
pp. 3666
Author(s):  
Tsu Chiang Lei ◽  
Shiuan Wan ◽  
Shih-Chieh Wu ◽  
Hsin-Ping Wang
Keyword(s):  
Image Classification ◽  
Satellite Image ◽  
Image Data ◽  
Support Vector ◽  
Probability Models ◽  
Aerial Photos ◽  
Sensing Technology ◽  
Kappa Value ◽  
Paddy Area

Remote sensing technology has rendered lots of information in agriculture. It has usually been used to monitor paddy growing ecosystems in the past few decades. However, there are uncertainties in data fusion techniques which can be resolved in image classification on paddy rice. In this study, a series of learning concepts integrated by a probability progress Fuzzy Dempster-Shafer (FDS) analysis is presented to upgrade various models and different types of image data which is the goal of this study. More specifically, the study utilized the FDS to generate a series of probability models in the classification of the system. In addition, Logistic Regression (LR), Support Vector Machine (SVM), and Neural Network (NN) approaches are employed into the developed FDS system. Furthermore, two different image types are Satellite Image and Aerial Photo used as the analysis material. The overall classification accuracy has been improved to 97.27%, and the kappa value is 0.93. The overall accuracy of the paddy field image classification for a multi-period of mid-scale satellite images is between 85% and 90%. The overall accuracy of the classification using multi-spectral numerical aerial photos can be between 91% and 95%. The FDS improves the accuracy of the above image classification results.

scholarly journals Intuitionistic fuzzy negations and their use in image classification

2020 ◽  
Vol 26 (3) ◽  
pp. 22-32
Author(s):  
Alžbeta Michalíková ◽  
◽  
Keyword(s):  
Fuzzy Sets ◽  
Image Classification ◽  
Specific Problem ◽  
Image Data ◽  
Intuitionistic Fuzzy Sets ◽  
Intuitionistic Fuzzy ◽  
Membership Value ◽  
Classification Of Images

In this paper, the problem of classification of images is discussed. Our specific problem is that we need to classify tire images into selected classes. The classes are characterized by some patterns. In the first step images are represented as the vectors. Then the membership and non-membership value to each coordinate of the vector is calculated and the theory of intuitionistic fuzzy sets is used. In [7] the classification of images was performed with respect to the valued of so called Sim function, which was defined as a ratio of distance between pattern data and image data and distance between pattern data and the complement of image data. The complement of image data was obtained by using specific intuitionistic fuzzy negation. In [2] a list of 53 intuitionistic fuzzy negations was presented. We have decided to use some of these negations to improve the results of classification.

Hyperspectral Image Classification via Discriminative Sparse Representation with Extended LBP Texture

2014 ◽  
Vol 989-994 ◽  
pp. 3885-3888 ◽  
Author(s):  
Yue Mei Ren ◽  
Yan Ning Zhang ◽  
Wei Wei
Keyword(s):  
Sparse Representation ◽  
Image Classification ◽  
Optimization Problem ◽  
Hyperspectral Image ◽  
Local Binary Patterns ◽  
Hyperspectral Image Classification ◽  
Texture Information ◽  
Classification Framework ◽  
Representation Error

Hyperspectral images (HSI) have rich texture information, so combining texture information and image spectral information can improve the recognition accuracy. Sparse representation has significant success in image classification. In this paper, we propose a new discriminative sparse-based classification framework using spectral data and extended Local Binary Patterns (LBP) texture. Firstly, we propose an extended LBP coding for HSI classification. Then we formulate an optimization problem that combines the objective function of classification with the representation error by sparsity. Furthermore, we use a procedure similar to K-SVD algorithm to learn the discriminative dictionary. The experimental results show that the proposed discriminative spasity-based classification of image including the extended LBP texture outperforms the classical HSI classification algorithms.

CNN-based Classification of Degraded Images

2020 ◽  
Vol 2020 (10) ◽  
pp. 28-1-28-7 ◽  
Author(s):  
Kazuki Endo ◽  
Masayuki Tanaka ◽  
Masatoshi Okutomi
Keyword(s):  
Neural Networks ◽  
Image Restoration ◽  
Image Classification ◽  
Convolutional Neural Networks ◽  
Deep Convolutional Neural Networks ◽  
Alternative Approach ◽  
Degraded Image ◽  
Degraded Images ◽  
Straightforward Approach

Classification of degraded images is very important in practice because images are usually degraded by compression, noise, blurring, etc. Nevertheless, most of the research in image classification only focuses on clean images without any degradation. Some papers have already proposed deep convolutional neural networks composed of an image restoration network and a classification network to classify degraded images. This paper proposes an alternative approach in which we use a degraded image and an additional degradation parameter for classification. The proposed classification network has two inputs which are the degraded image and the degradation parameter. The estimation network of degradation parameters is also incorporated if degradation parameters of degraded images are unknown. The experimental results showed that the proposed method outperforms a straightforward approach where the classification network is trained with degraded images only.

Sign in / Sign up

Export Citation Format

Share Document