scholarly journals On Some Desired Properties of Data Augmentation by Illumination Simulation for Color Constancy

2020 ◽  
Author(s):  
Nikola Banić ◽  
Karlo Koščević ◽  
Marko Subašić ◽  
Sven Lončarić
Keyword(s):  
Data Augmentation ◽  
Color Constancy ◽  
Ground Truth ◽  
Estimation Methods ◽  
Small Data ◽  
Digital Cameras ◽  
Illumination Estimation ◽  
Scene Illumination ◽  
Almost All ◽  
Simulated Images

Computational color constancy is used in almost all digital cameras to reduce the influence of scene illumination on object colors. Many of the highly accurate published illumination estimation methods use deep learning, which relies on large amounts of images with known ground-truth illuminations. Since the size of the appropriate publicly available training datasets is relatively small, data augmentation is often used also by simulating the appearance of a given image under another illumination. Still, there are practically no reports on any desired properties of such simulated images or on the limits of their usability. In this paper, several experiments for determining some of these properties are proposed and conducted by comparing the behavior of the simplest illumination estimation methods on images of the same scenes obtained under real illuminations and images obtained through data augmentation. The experimental results are presented and discussed.

A Flying Gray Ball Multi-illuminant Image Dataset for Color Research

2020 ◽  
Vol 64 (5) ◽  
pp. 50411-1-50411-8
Author(s):  
Hoda Aghaei ◽  
Brian Funt
Keyword(s):  
Machine Vision ◽  
Spectral Reflectance ◽  
Color Constancy ◽  
Ground Truth ◽  
Practical Approach ◽  
Post Processing ◽  
Illumination Estimation ◽  
Processing Step ◽  
Image Dataset

Abstract For research in the field of illumination estimation and color constancy, there is a need for ground-truth measurement of the illumination color at many locations within multi-illuminant scenes. A practical approach to obtaining such ground-truth illumination data is presented here. The proposed method involves using a drone to carry a gray ball of known percent surface spectral reflectance throughout a scene while photographing it frequently during the flight using a calibrated camera. The captured images are then post-processed. In the post-processing step, machine vision techniques are used to detect the gray ball within each frame. The camera RGB of light reflected from the gray ball provides a measure of the illumination color at that location. In total, the dataset contains 30 scenes with 100 illumination measurements on average per scene. The dataset is available for download free of charge.

scholarly journals SDD-CNN: Small Data-Driven Convolution Neural Networks for Subtle Roller Defect Inspection

2019 ◽  
Vol 9 (7) ◽  
pp. 1364 ◽  
Author(s):  
Xiaohang Xu ◽  
Hong Zheng ◽  
Zhongyuan Guo ◽  
Xiongbin Wu ◽  
Zhaohui Zheng
Keyword(s):  
Data Augmentation ◽  
Surface Defects ◽  
Ground Truth ◽  
Data Driven ◽  
Convergence Time ◽  
Smart Manufacturing ◽  
Small Data ◽  
Defect Inspection ◽  
Bearing Defects ◽  
Low Probability

Roller bearings are some of the most critical and widely used components in rotating machinery. Appearance defect inspection plays a key role in bearing quality control. However, in real industries, bearing defects are usually extremely subtle and have a low probability of occurrence. This leads to distribution discrepancies between the number of positive and negative samples, which makes intelligent data-driven inspection methods difficult to develop and deploy. This paper presents a small data-driven convolution neural network (SDD-CNN) for roller subtle defect inspection via an ensemble method for small data preprocessing. First, label dilation (LD) is applied to solve the problem of an imbalance in class distribution. Second, a semi-supervised data augmentation (SSDA) method is proposed to extend the dataset in a more efficient and controlled way. In this method, a coarse CNN model is trained to generate ground truth class activation and guide the random cropping of images. Third, four variants of the CNN model, namely, SqueezeNet v1.1, Inception v3, VGG-16, and ResNet-18, are introduced and employed to inspect and classify the surface defects of rollers. Finally, a rich set of experiments and assessments is conducted, indicating that these SDD-CNN models, particularly the SDD-Inception v3 model, perform exceedingly well in the roller defect classification task with a top-1 accuracy reaching 99.56%. In addition, the convergence time and classification accuracy for an SDD-CNN model achieve significant improvement compared to that for the original CNN. Overall, using an SDD-CNN architecture, this paper provides a clear path toward a higher precision and efficiency for roller defect inspection in smart manufacturing.

scholarly journals An Illumination Estimation Algorithm based on Outdoor Scene Classification

2020 ◽  
Vol 14 ◽  
Keyword(s):  
Color Constancy ◽  
Estimation Algorithm ◽  
General Algorithm ◽  
Support Vector ◽  
Optimal Algorithms ◽  
Scene Classification ◽  
Illumination Estimation ◽  
Scene Illumination ◽  
Rgb Values ◽  
Better Than

The illumination estimation algorithm belongs to the field of color constancy, aiming to restoring the color of image through estimating the RGB of scene illumination. In different scenarios, the performance of a general algorithm varies greatly. If the scene can be predicted, it can be inferred that the scenarios related optimal algorithms is better than a general algorithm for estimating illumination. In this paper, a novel algorithm based on outdoor scene classification was proposed: firstly, the support vector machine (svm) classifiers was used to identify scene types , and then the scenarios related optimal algorithms was selected, finally used the RGB values of scene illumination were calculated.

scholarly journals Green Stability Assumption: Unsupervised Learning for Statistics-Based Illumination Estimation

2018 ◽  
Vol 4 (11) ◽  
pp. 127 ◽  
Author(s):  
Nikola Banić ◽  
Sven Lončarić
Keyword(s):  
Estimation Method ◽  
Digital Camera ◽  
Ground Truth ◽  
Estimation Methods ◽  
Illumination Estimation ◽  
Processing Pipeline ◽  
Whole Process ◽  
Calibrated Images ◽  
Parameter Values ◽  
Fine Tune

In the image processing pipeline of almost every digital camera, there is a part for removing the influence of illumination on the colors of the image scene. Tuning the parameter values of an illumination estimation method for maximal accuracy requires calibrated images with known ground-truth illumination, but creating them for a given sensor is time-consuming. In this paper, the green stability assumption is proposed that can be used to fine-tune the values of some common illumination estimation methods by using only non-calibrated images. The obtained accuracy is practically the same as when training on calibrated images, but the whole process is much faster since calibration is not required and thus time is saved. The results are presented and discussed. The source code website is provided in Section Experimental Results.

Evaluating Colour Constancy on the new MIST dataset of Multi-Illuminant Scenes

2019 ◽  
Vol 2019 (1) ◽  
pp. 108-113 ◽  
Author(s):  
Xiangpeng Hao ◽  
Brian Funt ◽  
Hanxiao Jiang
Keyword(s):  
Ground Truth ◽  
Estimation Methods ◽  
Colour Constancy ◽  
Uniform Illumination ◽  
Full Spectrum ◽  
Test Set ◽  
Illumination Estimation ◽  
Image Test ◽  
Case Based ◽  
Better Than

A new image test set of synthetically generated, full-spectrum images with pixelwise ground truth has been developed to aid in the evaluation of illumination estimation methods for colour constancy. The performance of 9 illumination methods is reported for this dataset along and compared to the optimal single-illuminant estimate. None of the methods specifically designed to handle multi-illuminant scenes is found to perform any better than the optimal single-illuminant case based on completely uniform illumination.

In vitro effectiveness of biapenem against IMP-producing Enterobacteriaceae

2021 ◽  
Vol 70 (10) ◽  
Author(s):  
Kazuyoshi Gotoh ◽  
Makoto Miyoshi ◽  
I Putu Bayu Mayura ◽  
Koji Iio ◽  
Osamu Matsushita ◽  
...  
Keyword(s):  
Therapeutic Option ◽  
Small Data ◽  
Limited Data ◽  
Data Set ◽  
Content Type ◽  
Link Type ◽  
Almost All ◽  
New Treatments ◽  
Time Kill

The options available for treating infections with carbapenemase-producing Enterobacteriaceae (CPE) are limited; with the increasing threat of these infections, new treatments are urgently needed. Biapenem (BIPM) is a carbapenem, and limited data confirming its in vitro killing effect against CPE are available. In this study, we examined the minimum inhibitory concentrations (MICs) and minimum bactericidal concentrations (MBCs) of BIPM for 14 IMP-1-producing Enterobacteriaceae strains isolated from the Okayama region in Japan. The MICs against almost all the isolates were lower than 0.5 µg ml−1, indicating susceptibility to BIPM, while approximately half of the isolates were confirmed to be bacteriostatic to BIPM. However, initial killing to a 99.9 % reduction was observed in seven out of eight strains in a time–kill assay. Despite the small data set, we concluded that the in vitro efficacy of BIPM suggests that the drug could be a new therapeutic option against infection with IMP-producing CPE.

scholarly journals Time Series Modelling of Academic Employee Commitment of a Sub-Saharan African University

2020 ◽  
pp. 60-76
Author(s):  
Olukemi Olufunmilola Asemota ◽  
Godwin Norense Osarumwense Asemota
Keyword(s):  
Employee Commitment ◽  
Future Research ◽  
Small Data ◽  
Study Objective ◽  
Material Resources ◽  
Time Series Modelling ◽  
Parallel Network ◽  
Sub Saharan ◽  
Almost All ◽  
Larger Sample

The study objective is to see how human resource management (HRM) could rely on small data evidence-based analytics to gauge employee commitment in a sub-Saharan African University. A 7-point Likert scale questionnaire on academic employee commitment in Kenya Public Universities was designed, validated and pilot tested. Out of around 60 questionnaires administered, only 31 responses were obtained before the Corona Virus (COVID-19) pandemic lockdowns in Kenya. The responses were subjected to the Modeler analyses using the statistical package for social sciences (SPSS version 21) to generate twelve optimal ARIMA (0,0,0) models for further statistical analyses. Results indicate 46.7% of employees want to spend the rest of their career in the organisation, over 61.2% of employees felt alienated and 34.9% were not emotionally attached. Around 59.3%, 64.0% and almost all employees tested on different metrics have difficulty leaving the organisation now. Although 28.9% of employees could leave abruptly, 64.6% of employees felt acculturated and 29.7% would remain at all costs. Overall, add-on effects of willingness to stay and bear with the organisation, emotional attachment, alienation, moral obligation, beneficial to remain, discouragement levels, organisational culture and being sold out to organisation could influence employee commitment levels. Thus, contributing to the HRM field, especially because the twelve-layered cascade of a series-parallel network made up of ladder and lattice structures of shared human and material resources management was used to deduce the Jackson’s theorem. Future research shall consider larger sample sizes to enable us to confirm or refute the conclusions derived in this study.

scholarly journals WHSP-Net: A Weakly-Supervised Approach for 3D Hand Shape and Pose Recovery from a Single Depth Image

Sensors ◽  
2019 ◽  
Vol 19 (17) ◽  
pp. 3784 ◽  
Author(s):  
Jameel Malik ◽  
Ahmed Elhayek ◽  
Didier Stricker
Keyword(s):  
Pose Estimation ◽  
Synthetic Data ◽  
Ground Truth ◽  
Real Data ◽  
Depth Image ◽  
Estimation Methods ◽  
Hand Shape ◽  
Pose Recovery ◽  
Real World Datasets ◽  
Weakly Supervised

Hand shape and pose recovery is essential for many computer vision applications such as animation of a personalized hand mesh in a virtual environment. Although there are many hand pose estimation methods, only a few deep learning based algorithms target 3D hand shape and pose from a single RGB or depth image. Jointly estimating hand shape and pose is very challenging because none of the existing real benchmarks provides ground truth hand shape. For this reason, we propose a novel weakly-supervised approach for 3D hand shape and pose recovery (named WHSP-Net) from a single depth image by learning shapes from unlabeled real data and labeled synthetic data. To this end, we propose a novel framework which consists of three novel components. The first is the Convolutional Neural Network (CNN) based deep network which produces 3D joints positions from learned 3D bone vectors using a new layer. The second is a novel shape decoder that recovers dense 3D hand mesh from sparse joints. The third is a novel depth synthesizer which reconstructs 2D depth image from 3D hand mesh. The whole pipeline is fine-tuned in an end-to-end manner. We demonstrate that our approach recovers reasonable hand shapes from real world datasets as well as from live stream of depth camera in real-time. Our algorithm outperforms state-of-the-art methods that output more than the joint positions and shows competitive performance on 3D pose estimation task.

scholarly journals Logo-2K+: A Large-Scale Logo Dataset for Scalable Logo Classification

2020 ◽  
Vol 34 (04) ◽  
pp. 6194-6201
Author(s):  
Jing Wang ◽  
Weiqing Min ◽  
Sujuan Hou ◽  
Shengnan Ma ◽  
Yuanjie Zheng ◽  
...  
Keyword(s):  
Image Recognition ◽  
Real World ◽  
Large Scale ◽  
Data Augmentation ◽  
Ground Truth ◽  
Classification Task ◽  
The Real ◽  
Product Recommendation ◽  
Contextual Advertising ◽  
Benchmark Datasets

Logo classification has gained increasing attention for its various applications, such as copyright infringement detection, product recommendation and contextual advertising. Compared with other types of object images, the real-world logo images have larger variety in logo appearance and more complexity in their background. Therefore, recognizing the logo from images is challenging. To support efforts towards scalable logo classification task, we have curated a dataset, Logo-2K+, a new large-scale publicly available real-world logo dataset with 2,341 categories and 167,140 images. Compared with existing popular logo datasets, such as FlickrLogos-32 and LOGO-Net, Logo-2K+ has more comprehensive coverage of logo categories and larger quantity of logo images. Moreover, we propose a Discriminative Region Navigation and Augmentation Network (DRNA-Net), which is capable of discovering more informative logo regions and augmenting these image regions for logo classification. DRNA-Net consists of four sub-networks: the navigator sub-network first selected informative logo-relevant regions guided by the teacher sub-network, which can evaluate its confidence belonging to the ground-truth logo class. The data augmentation sub-network then augments the selected regions via both region cropping and region dropping. Finally, the scrutinizer sub-network fuses features from augmented regions and the whole image for logo classification. Comprehensive experiments on Logo-2K+ and other three existing benchmark datasets demonstrate the effectiveness of proposed method. Logo-2K+ and the proposed strong baseline DRNA-Net are expected to further the development of scalable logo image recognition, and the Logo-2K+ dataset can be found at https://github.com/msn199959/Logo-2k-plus-Dataset.

Beyond White: Ground Truth Colors for Color Constancy Correction

2015 ◽  
Author(s):  
Dongliang Cheng ◽  
Brian Price ◽  
Scott Cohen ◽  
Michael S. Brown
Keyword(s):  
Color Constancy ◽  
Ground Truth
Sign in / Sign up

Export Citation Format

Share Document