scholarly journals Effects of Background Color, Flash and Exposure Value on the Accuracy of Smartphone-Based Pill Recognition System Using Deep Convolutional Neural Network (Preprint)

2020 ◽  
Author(s):  
KyeongMin Cha
Keyword(s):  
Real World ◽  
Color Difference ◽  
Recognition System ◽  
Reference Image ◽  
White Background ◽  
Factors Affecting ◽  
The Real ◽  
Black Background ◽  
The Difference ◽  
World Image

BACKGROUND It is difficult to develop a drug image recognition system due to the difference of the pill color influenced by external environmental factors such as the illumination or presence of flash. OBJECTIVE In this study, we wanted to see how the difference in color between the reference image and the real-world image affects the accuracy in pill recognition under 12 real-world conditions according to the background colors, presence of flash, and exposure values (EV). METHODS We used 19 medications with different features of colors, shapes, and dosages. The average color difference was calculated based on the color distance between the reference image and the real-world image. RESULTS In the case of the black background, as the exposure value lowered, the accuracy of top-1 and top-5 increased independently of the presence of flash. The top-5 accuracy in black background increased from 26.8% to 72.6% with the flash on and from 29.5% to 76.8% with the flash off as EV decreased as well. On the other hand, top-5 accuracy was 62.1% to 78.4% in white background with the flash on. The best top-1 accuracy was 51.1 % in the white background, flash on, and EV+2.0. The best top-5 accuracy was 78.4% in the white background, flash on, and EV0. CONCLUSIONS The accuracy generally increased as the color difference decreased except in the case of black background and EV-2.0. This study reveals that the background colors, presence of flash, and exposure values in real-world conditions are important factors affecting the performance of a pill recognition model.

scholarly journals Difference between the Real World and Virtual World

Proceedings ◽  
2020 ◽  
Vol 47 (1) ◽  
pp. 35
Author(s):  
Wei Wang
Keyword(s):  
Virtual Reality ◽  
Real World ◽  
Virtual World ◽  
Actual World ◽  
Scientific Representation ◽  
The Real ◽  
The Difference

The development of virtual reality brings an old and historic question on the difference between the real world and unreal world. In this paper, starting from the concept of representation, I argued that what we call “virtual reality” is a representation of an actual or non-actual world and the criterion of difference between the “real world” and “virtual reality” is whether we present it with the intention of using it as a representation. After that, the thesis is demonstrated again from different theories of scientific representation. Therefore, the intuitive distinction between the “real world” and “virtual reality” can be drawn on the epistemological criterion; that is to say, the virtual world is a representation while the real world is not.

scholarly journals Study of the correlation of factors affecting frequency of social activity transfer from virtual environment to real-world environment and vice versa

2019 ◽  
Vol 70 ◽  
pp. 08046
Author(s):  
Anton Zagranichniy
Keyword(s):  
Virtual Environment ◽  
Real World ◽  
Social Activity ◽  
Subjective Assessment ◽  
Demographic Characteristics ◽  
Factors Affecting ◽  
The Real ◽  
Size Number ◽  
Environment Factor ◽  
World Environment

The article presents research results demonstrating interrelation between factors affecting frequency of social activity transfer from the virtual environment to the real-world one and vice versa. In the course of the study we investigated 19 different factors, including socio-demographic characteristics, amount and specificity of contacts in each of the environments, subjective assessment of social activity characteristics in various environments. The study involved 214 respondents aged 15 to 24 from the cities of Balakovo, Saratov, and Moscow. We analysed and interpreted the correlation interrelation via social activity transfer from one environment to another and by such factors as: place of residence size; number of friends in the virtual environment; factor regarding frequency of misconduct situations that were followed by moral responsibility in the real environment; factor of compliance with social norms in the virtual environment.

Different Engines

2017 ◽  
Author(s):  
Gary Westfahl
Keyword(s):  
Science Fiction ◽  
Real World ◽  
The Real ◽  
Alternate History ◽  
Film Version ◽  
Bruce Sterling ◽  
Song Lyrics ◽  
The Difference ◽  
First Offers

This chapter examines William Gibson's The Difference Engine, a collaboration with Bruce Sterling, as well as his screenplays, poetry, song lyrics, and nonfiction. Sterling used an irresistibly marketable concept for The Difference Engine: a novel by what he could describe as the two leading cyberpunk authors that would appealingly blend three popular subgenres of science fiction—cyberpunk, alternate history, and “steampunk” literature. Despite the prominence of cyberspace in his Sprawl trilogy, Gibson claimed that he has “never really been very interested in computers themselves.” This chapter first offers a reading of The Difference Engine before discussing Gibson's screenplays written for Hollywood in the late 1980s, including one for a proposed Alien 3 film and another for the film version of Johnny Mnemonic. It also considers Gibson's poems such as “The Beloved: Voices for Three Heads,” his ventures into writing song lyrics, and the approach he used in some of his later nonfiction works: looking at the real world in terms of science fiction, conveying that we indeed live in a science fiction world.

Further Considerations of Classification-Oriented and Approximation-Oriented Rough Sets in Generalized Settings

2010 ◽  
Vol 4 (2) ◽  
pp. 12-34
Author(s):  
Masahiro Inuiguchi
Keyword(s):  
Real World ◽  
Rough Sets ◽  
Decision Rules ◽  
Point Of View ◽  
Inverse Relation ◽  
The Real ◽  
The Difference

Rough sets can be interpreted in two ways: classification of objects and approximation of a set. From this point of view, classification-oriented and approximation-oriented rough sets have been proposed. In this paper, the author reconsiders those two kinds of rough sets with reviewing their definitions, properties and relations. The author describes that rough sets based on positive and negative extensive relations are mathematically equivalent but it is important to consider both because they obtained positive and negative extensive relations are not always in inverse relation in the real world. The difference in size of granules between union-based and intersection-based approximations is emphasized. Moreover, the types of decision rules associated with those rough sets are shown.

Audiovisual Integration of Natural Auditory and Visual Stimuli in the Real-World Situation

2013 ◽  
pp. 337-344
Author(s):  
Xiaoyu Tang ◽  
Yulin Gao ◽  
Weiping Yang ◽  
Ming Zhang ◽  
Jinglong Wu
Keyword(s):  
Real World ◽  
Visual Stimuli ◽  
Neural Mechanism ◽  
Audiovisual Integration ◽  
Semantic Matching ◽  
Factors Affecting ◽  
The Real ◽  
Emotional Factors ◽  
The Future ◽  
Real World Situation

Bimodal audiovisual (AV) stimuli are detected or discriminated faster and more accurately than either visual or auditory unimodal stimuli. This effect is called audiovisual integration. Recently, researchers have been increasingly focused on the audiovisual integration of natural, auditory, and visual stimuli in real-world situations. There are some differences between audiovisual integration of naturalistic stimuli and non-naturalistic stimuli, such as the time of occurrence of audiovisual integration, and the neural mechanism. Factors affecting audiovisual integration in real-world situations are summarized here, with particular focus on temporal asynchrony and semantic matching. Stimuli of audiovisual integration in the real-world situation should be controlled strictly, especially emotional factors, familiarity factors, semantic matching, and the match of the naturalistic stimuli and non-naturalistic stimuli. In the future, researchers should study the influence of attention on audiovisual integration and the mechanism of audiovisual integration with naturalistic stimuli in the real-world situation.

scholarly journals IMPROVING SMARTPHONE POSITION AND ATTITUDE FOR GEOSPATIAL AUGMENTED REALITY APPLICATIONS

2020 ◽  
Vol XLIII-B4-2020 ◽  
pp. 559-565
Author(s):  
J. Chung ◽  
H. Kim ◽  
J. Cheon ◽  
I. Lee
Keyword(s):  
Augmented Reality ◽  
Coordinate System ◽  
Real World ◽  
Tracking Error ◽  
Correction Method ◽  
High Accuracy ◽  
Reference Image ◽  
Absolute Position ◽  
The Real ◽  
Reference Images

Abstract. Augmented reality is a technology that visualizes and synthesizes virtual objects and information in the real world. Augmented reality can provide useful information to the real world realistically. As the investment and demand for augmented reality increase, many researches have been conducted to visualize objects based on ground coordinate system such as cadastral information and underground facilities using augmented reality. In order to visualize objects based on the ground coordinate system on a smartphone using augmented reality, high accuracy of the position and attitude of the smartphone is essential. Accordingly, this study proposed position and attitude correction method for the first image using reference images and single photo resection. Then, the absolute position of the entire image was estimated using the first calibrated image and the tracking algorithm. When the reference image-based correction method was used, the accuracy was 0.74m, 0.94m. And when the single photo resection correction method was used, the accuracy was 3.13m, 1.24m. The method presented in this study showed higher accuracy when only the sensor was used, but it was confirmed that errors in position and attitude occur as the tracking error accumulates.

scholarly journals Translators as Well as Thinkers: Teaching of Journalistic Translation in Hong Kong1

2006 ◽  
Vol 51 (3) ◽  
pp. 611-619 ◽  
Author(s):  
Defeng Li
Keyword(s):  
Hong Kong ◽  
Empirical Evidence ◽  
Professional Practice ◽  
Real World ◽  
The Real ◽  
The World ◽  
Translator Training ◽  
The Difference ◽  
Translation Methods

Abstract Hong Kong is probably one of the most exciting places in the world to study translation as a student or a researcher. Seven out of the eight universities offer translation degrees. Among others, journalistic translation has always been one of the most popular courses for students. However, students have often felt underprepared in journalistic translation even after taking some related courses. This study argues, with the support of empirical evidence that one of the major reasons accountable for this is the gap between institutional translator training and the real world of professional translation, which, in the context of journalistic translation, manifests itself as the difference in translation methods taught in translation programs and used in professional practice. The author further contends that this gap needs to be bridged in order to better prepare student translators for the market. Recommendations are also made as to how the gap can be narrowed or bridged.

scholarly journals The pigmentary effector system - IX. The receptor fields of the teleostean visual response

1940 ◽  
Vol 128 (852) ◽  
pp. 317-342 ◽  
Keyword(s):  
Colour Change ◽  
Primary Response ◽  
Senior Author ◽  
The Other ◽  
White Background ◽  
Visual Response ◽  
Local Response ◽  
Black Background ◽  
Effector System ◽  
The Difference

Both among vertebrates and among Crustacea one commonly meets with two co-existent modes of chromatic response to photic stimulation. One is the dispersion (“expansion”) of melanophores and certain other chromatophores under the local (primary) influence of light on the skin. The other is aggregation (“contraction”) of melanophores and of certain other chromatophores when light reflected from the surroundings impinges on the organs of vision, in contradistinction to dispersion (“expansion”) when only overhead illumination strikes the eye. Though the primary (local) response is usually subordinate to and is more or less overruled by the secondary or visual response, the relative importance of the two components varies within wide limits. In particular species either may be negligible in comparison with the other. When, as more commonly, both contribute significantly to the observed result, a blinded animal is necessarily more pale in darkness than in light. Probably this fact influenced all the earlier investigators who, including the senior author (1924), paid little attention to the otherwise paradoxical fact that animals kept on a “black background” (i. e. under conditions of overhead illumination in light absorbing surroundings) are much darker than animals kept in similar conditions with no light at all. Subsequent analysis of the normal course of colour change, both in vertebrates and in Crustaces, has shown that this is also true of species which have no appreciable primary response, and that the difference generally exceeds the limits of variation consistent with the co-existence of a detectable primary response. It is therefore clear that the difference between the “white background” response and the “black background” response is not due to intensity alone.

scholarly journals Sensitivity analysis for mistakenly adjusting for mediators in estimating total effect in observational studies

BMJ Open ◽  
2017 ◽  
Vol 7 (11) ◽  
pp. e015640 ◽  
Author(s):  
Tingting Wang ◽  
Hongkai Li ◽  
Ping Su ◽  
Yuanyuan Yu ◽  
Xiaoru Sun ◽  
...  
Keyword(s):  
Sensitivity Analysis ◽  
Logistic Regression ◽  
Real World ◽  
Observational Studies ◽  
Total Effect ◽  
Causal Relationships ◽  
The Real ◽  
Limited Knowledge ◽  
Causal Diagrams ◽  
The Difference

ObjectivesIn observational studies, epidemiologists often attempt to estimate the total effect of an exposure on an outcome of interest. However, when the underlying diagram is unknown and limited knowledge is available, dissecting bias performances is essential to estimating the total effect of an exposure on an outcome when mistakenly adjusting for mediators under logistic regression. Through simulation, we focused on six causal diagrams concerning different roles of mediators. Sensitivity analysis was conducted to assess the bias performances of varying across exposure-mediator effects and mediator-outcome effects when adjusting for the mediator.SettingBased on the causal relationships in the real world, we compared the biases of varying across the effects of exposure-mediator with those of varying across the effects of mediator-outcome when adjusting for the mediator. The magnitude of the bias was defined by the difference between the estimated effect (using logistic regression) and the total effect of the exposure on the outcome.ResultsIn four scenarios (a single mediator, two series mediators, two independent parallel mediators or two correlated parallel mediators), the biases of varying across the effects of exposure-mediator were greater than those of varying across the effects of mediator-outcome when adjusting for the mediator. In contrast, in two other scenarios (a single mediator or two independent parallel mediators in the presence of unobserved confounders), the biases of varying across the effects of exposure-mediator were less than those of varying across the effects of mediator-outcome when adjusting for the mediator.ConclusionsThe biases were more sensitive to the variation of effects of exposure-mediator than the effects of mediator-outcome when adjusting for the mediator in the absence of unobserved confounders, while the biases were more sensitive to the variation of effects of mediator-outcome than those of exposure-mediator in the presence of an unobserved confounder.

Evaluator as a Critical Participant in an Interagency Collaboration: A Case Study

2000 ◽  
Vol 22 (2) ◽  
pp. 18-22
Author(s):  
Barbara Knox-Seith
Keyword(s):  
Public Relations ◽  
Real World ◽  
Interagency Collaboration ◽  
Staff Time ◽  
Lead Agency ◽  
The Real ◽  
The Difference

The day after I presented an earlier version of this article (in the session "Landing on Your Feet in the Real World: Anthropologists as Evaluators" at the SfAA annual meetings in Seattle, March, 1997) I spoke by phone with Hilary Stern, the director of CASA Latina, the lead agency on the project discussed in the following pages. She summarized her experiences with evaluation: The evaluation you did for us was the first helpful evaluation we've had, and we've participated in many. Other agencies' experiences are similar to ours. I was really glad that I could tell other people about our experience [at a session on evaluation at a conference on ESLIadult education]. It was the only positive example anyone was able to provide. In most evaluations, evaluators have come from outside. They impose on staff time, and sometimes they don't even give the agency the results. When they do, the information isn't of value to the agency: they tell us what we already know; they don't tell us about things we want to know, things that matter to us. The difference with this evaluation is that it met our agenda. We decided we wanted the evaluation, and we selected the evaluator. It contributed to the success of our project and to our goals as an agency. Other evaluations were done to meet the agenda of the researchers. We agreed to participate in them as a matter of good public relations. Other than that, they're a waste of our time. I'm glad we had the experience of this evaluation. It shows that evaluation can be useful. I hope that you will publish your paper about it as a model and inspiration to others. — [paraphrase of] Hilary Stern, from phone conversation on March 8, 1997

Sign in / Sign up

Export Citation Format

Share Document