scholarly journals Automated Identification Algorithm Using CNN for Computer Vision in Smart Refrigerators

2022 ◽  
Vol 71 (2) ◽  
pp. 3337-3353
Author(s):  
Pulkit Jain ◽  
Paras Chawla ◽  
Mehedi Masud ◽  
Shubham Mahajan ◽  
Amit Kant Pandit
Keyword(s):  
Computer Vision ◽  
Identification Algorithm ◽  
Automated Identification

scholarly journals Thinking like a naturalist: enhancing computer vision of citizen science images by harnessing contextual data

2019 ◽  
Author(s):  
J. Christopher D. Terry ◽  
Helen E. Roy ◽  
Tom A. August
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Computer Vision ◽  
Contextual Information ◽  
Network Models ◽  
List Type ◽  
British Isles ◽  
Automated Identification ◽  
Neural Network Models ◽  
Contextual Data

AbstractThe accurate identification of species in images submitted by citizen scientists is currently a bottleneck for many data uses. Machine learning tools offer the potential to provide rapid, objective and scalable species identification for the benefit of many aspects of ecological science. Currently, most approaches only make use of image pixel data for classification. However, an experienced naturalist would also use a wide variety of contextual information such as the location and date of recording.Here, we examine the automated identification of ladybird (Coccinellidae) records from the British Isles submitted to the UK Ladybird Survey, a volunteer-led mass participation recording scheme. Each image is associated with metadata; a date, location and recorder ID, which can be cross-referenced with other data sources to determine local weather at the time of recording, habitat types and the experience of the observer. We built multi-input neural network models that synthesise metadata and images to identify records to species level.We show that machine learning models can effectively harness contextual information to improve the interpretation of images. Against an image-only baseline of 48.2%, we observe a 9.1 percentage-point improvement in top-1 accuracy with a multi-input model compared to only a 3.6% increase when using an ensemble of image and metadata models. This suggests that contextual data is being used to interpret an image, beyond just providing a prior expectation. We show that our neural network models appear to be utilising similar pieces of evidence as human naturalists to make identifications.Metadata is a key tool for human naturalists. We show it can also be harnessed by computer vision systems. Contextualisation offers considerable extra information, particularly for challenging species, even within small and relatively homogeneous areas such as the British Isles. Although complex relationships between disparate sources of information can be profitably interpreted by simple neural network architectures, there is likely considerable room for further progress. Contextualising images has the potential to lead to a step change in the accuracy of automated identification tools, with considerable benefits for large scale verification of submitted records.

Research on Volume Measurement Technology for Rail Tanker Based on Computer Vision

2012 ◽  
Vol 157-158 ◽  
pp. 646-651
Author(s):  
Ji Bin Zhao ◽  
Ren Bo Xia ◽  
Wei Jun Liu ◽  
Tao Fu ◽  
Yi Jun Huang ◽  
...  
Keyword(s):  
Computer Vision ◽  
Volume Measurement ◽  
Scattered Data ◽  
High Accuracy ◽  
Measurement Technology ◽  
Identification Algorithm ◽  
Localization Algorithm ◽  
Complex Environment ◽  
Accurate Identification ◽  
Novel Method

In this paper, a computer vision based volume measurement system for rail tanker is proposed. Considering the complex environment, we propose an accurate identification algorithm of coded point and a precise localization algorithm. By investigating the epipolar geometry among three views, this paper develops a novel method for metric reconstruction of a scene based on the trilinear relations. Through the method of ordering incomplete scattered data presented, we construct a series of cross-section contours for a tanker and achieve a precise reconstruction of the surface of the tanker. Experiments show that, the volume measurement method for rail tanker based on computer vision can be operated with simplicity and high accuracy.

scholarly journals Assessing the potential for deep learning and computer vision to identify bumble bee species from images

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Brian J. Spiesman ◽  
Claudio Gratton ◽  
Richard G. Hatfield ◽  
William H. Hsu ◽  
Sarina Jepsen ◽  
...  
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Web Application ◽  
Morphological Variability ◽  
Error Rates ◽  
Species Level ◽  
Bumble Bees ◽  
Classification Model ◽  
Automated Identification ◽  
Speed Accuracy

AbstractPollinators are undergoing a global decline. Although vital to pollinator conservation and ecological research, species-level identification is expensive, time consuming, and requires specialized taxonomic training. However, deep learning and computer vision are providing ways to open this methodological bottleneck through automated identification from images. Focusing on bumble bees, we compare four convolutional neural network classification models to evaluate prediction speed, accuracy, and the potential of this technology for automated bee identification. We gathered over 89,000 images of bumble bees, representing 36 species in North America, to train the ResNet, Wide ResNet, InceptionV3, and MnasNet models. Among these models, InceptionV3 presented a good balance of accuracy (91.6%) and average speed (3.34 ms). Species-level error rates were generally smaller for species represented by more training images. However, error rates also depended on the level of morphological variability among individuals within a species and similarity to other species. Continued development of this technology for automatic species identification and monitoring has the potential to be transformative for the fields of ecology and conservation. To this end, we present BeeMachine, a web application that allows anyone to use our classification model to identify bumble bees in their own images.

scholarly journals Automated identification of benthic epifauna with computer vision

2019 ◽  
Vol 615 ◽  
pp. 15-30 ◽  
Author(s):  
N Piechaud ◽  
C Hunt ◽  
PF Culverhouse ◽  
NL Foster ◽  
KL Howell
Keyword(s):  
Computer Vision ◽  
Automated Identification

scholarly journals Recognition of Human Face Emotions Detection Using Computer Vision Based Smart Images

2021 ◽  
Vol 10 (3) ◽  
pp. 1700-1704
Keyword(s):  
Computer Vision ◽  
Skin Color ◽  
High Impact ◽  
Human Face ◽  
Automated Identification ◽  
Desktop Application ◽  
Human Face Detection ◽  
The Face ◽  
Impact Area ◽  
Face Detector

Humans share a collection of basic and essential emotions that are expressed by facial expressions that seem to be consistent. The automated identification of humanemotion in imageswill be possible due to an algorithm that detects, extracts, and evaluates these facial expressions.The Face detector and recognizer application is a desktop application used to recognize human face emotions by using a computer vision based smart images. It consists of human face detection picture boxes and considers an image as an original image. It climaxes a face skin color, finds high impact area and identifies different emotions of the face from an image. The results of the image are depending upon the separation of Eyes & Lips movement of person. This is done by comparingface embedding vectors. It finds the smart photos focused on computer vision for successful identification of facial emotions in terms of various modes of speech such as smiling, shocking and weeping.

scholarly journals Channel-Quality Aware RFID Tag Identification Algorithm to Accommodate the Varying Channel Quality of IoT Environment

2019 ◽  
Vol 9 (2) ◽  
pp. 321 ◽  
Author(s):  
Yen-Hung Chen ◽  
Rui-Ze Hung ◽  
Lin-Kung Chen ◽  
Pi-Tzong Jan ◽  
Yin-Rung Su
Keyword(s):  
Radio Frequency Identification ◽  
Outdoor Environment ◽  
Identification System ◽  
Identification Algorithm ◽  
Automated Identification ◽  
Tag Identification ◽  
Channel Quality ◽  
Subway System ◽  
Frequency Identification ◽  
Simulation Results

Radio Frequency Identification (RFID) technique is broadly adopted as the automated identification system for the Internet of Things (IoT). Many RFID anti-collision algorithms were proposed to accelerate the tag identification process. However, they misjudged some unreadable slots which were due to collision instead of the bad channel condition, causing low bandwidth usage. This study proposes the Channel-quality Aware Query Tree algorithm (CAQT) to improve the identification performance in an error-prone channel environment. CAQT has three novel features: (1) it estimates the channel quality continuously and statistically in the rapidly changing channel quality environment; (2) it asks the tag for retransmission or to split the collide tags based on the channel quality; (3) the number of the groups which it splits tags is based on the estimated number of tags collide in current slot. The simulation results show that CAQT uses less than 31% slots compared with the conventional algorithms. The simulation results also demonstrate that CAQT provides enhanced performance when the channel quality is varying especially in outdoor environment, for example, ticket checking for railway or subway system.

Accuracy of an automated method of 3D soft tissue landmark detection

2020 ◽  
Author(s):  
Sanjana Baksi ◽  
Simon Freezer ◽  
Takeshi Matsumoto ◽  
Craig Dreyer
Keyword(s):  
Soft Tissue ◽  
Three Dimensional ◽  
Reference Plane ◽  
Identification Algorithm ◽  
Anatomical Landmarks ◽  
Automated Identification ◽  
Automated Method ◽  
Landmark Identification ◽  
Technological Advances ◽  
Third Dimension

Summary Introduction Due to technological advances, the quantification of facial form can now be done via three-dimensional (3D) photographic systems such as stereophotogrammetry. To enable comparison with traditional cephalometry, soft-tissue anatomical landmark definitions have been modified to incorporate the third dimension. Annotating these landmarks manually, however, is still a time-consuming and arduous process. Objective To develop an automated algorithm to accurately identify anatomical landmarks on three-dimensional soft tissue images. Methods Thirty 3dMD images were selected from a private orthodontic practice consisting of 15 males and 15 females between 9 and 17 years of age. The soft-tissue 3D images were aligned along a reference plane to setup a Cartesian coordinate system. Screened by 2 observers, 21 landmarks were manually annotated and their coordinates defined. An automated landmark identification algorithm, based on their anatomical definitions, was developed to compare the landmark validity against the manually identified counterpart. Results Twenty-one landmarks were analysed in detail. Inter-observer and intra-observer reliability using ICC was >0.9. The average difference and standard deviation between manual and automated methods for all landmarks was 3.2 and 1.64 mm, respectively. Sixteen out of twenty-one landmarks had a mean difference less than 4 mm. The landmarks of greatest agreement (≤2 mm) were mainly in the midline: pronasale, subnasale, subspinale, labiale superius, stomion, with the exception of chelion right. Five linear facial measurements were found to have moderate to good agreement between the manual and automated identification methods. Conclusions The developed algorithm was determined to be clinically relevant in the detection of midsagittal landmarks and associated measurements within the studied sample of adolescent Caucasian subjects.

Analyzing Language in Suicide Notes and Legacy Tokens

Crisis ◽  
2016 ◽  
Vol 37 (2) ◽  
pp. 140-147 ◽  
Author(s):  
Michael J. Egnoto ◽  
Darrin J. Griffin
Keyword(s):  
Text Analysis ◽  
Low Cost ◽  
Computer Software ◽  
Student Writing ◽  
Computer Assisted ◽  
Automated Identification ◽  
Completed Suicide ◽  
Suicide Notes ◽  
Self Harm ◽  
Harm To Others

Abstract. Background: Identifying precursors that will aid in the discovery of individuals who may harm themselves or others has long been a focus of scholarly research. Aim: This work set out to determine if it is possible to use the legacy tokens of active shooters and notes left from individuals who completed suicide to uncover signals that foreshadow their behavior. Method: A total of 25 suicide notes and 21 legacy tokens were compared with a sample of over 20,000 student writings for a preliminary computer-assisted text analysis to determine what differences can be coded with existing computer software to better identify students who may commit self-harm or harm to others. Results: The results support that text analysis techniques with the Linguistic Inquiry and Word Count (LIWC) tool are effective for identifying suicidal or homicidal writings as distinct from each other and from a variety of student writings in an automated fashion. Conclusion: Findings indicate support for automated identification of writings that were associated with harm to self, harm to others, and various other student writing products. This work begins to uncover the viability or larger scale, low cost methods of automatic detection for individuals suffering from harmful ideation.

Sign in / Sign up

Export Citation Format

Share Document