What is it and how quickly you can guess?

Abstract

-This article presents research on human interactions by using a methodology of gradually revealed images for recognition. The idea we measure here it to compare results of interactions while guessing on the image. In the results we show and discuss differences between sex of the participant and category of the quiz.

Keywords

• image composition
• interactions
• human behavior
• sociology of decisions

I. INTRODUCTION

Interactions are driven by many factors. During decision

processes our brain is focusing on some aspects of the reality which can be easily associated with the things we have in our memory or which surround us. This interactions are driven by some factors which we can associate and use for conclusions. Very often we must decide under pressure or under limited time. For these we can find some differences between man and woman, since not only a brain but also a sociology of decision is important. There are many articles presenting results from decision processes, where humans were asked to describe reactions from various inputs like sounds, images, unexpected situations, etc. In [ 1 ] was presented how humans react to the sound of aircraft. Authors measured reactions and described them in relation to the user. In [2] was presented how humans react to rewards and punishments in various situations, where as an exemplary social model was realized theory of Gray’s personality. In [3] was presented how humans react to uncontrolled results of situations they participate in, the authors were especially interested on relation of interactions to superstition. Very often in the research on human interactions are used images. From an image we are able to evaluate many emotions and also knowledge about the content. In [ 4 ] were discussed reactions to images, eg. by facial or behavioral features. In [ 5 ] authors discussed both reactions to images and also motivations that were diving people to interact in each way. In [ 6 ] were presented differences between man and woman reactions to children facial images, while in [ 7 ] differences were discussed on example of animals. An interesting aspects of psychological tendencies in our brains during choices were discussed in [ 8 ]. Image processing and interactions between machines based on human behavior are widely discussed in recent times. New articles present interesting ideas for selecting objects from images or to used models of human interactions to proceed communications Copyright held by the author(s). between robots and autonomous systems. All these ideas are helpful in the research on human behavior. In [ 9 ] was discussed how to use a composition of neural networks and heuristic methods to detect some features of fruits from images, while in [ 10 ] was proposed a method for automatic selection of bacteria. On the other hand there are many research on object oriented programming where cognitive aspects are modeled to increase code efficiency. In [ 11 ] authors proposed some complexity metrics based on cognitive models, while in [ 12 ] were presented research results on reactions to vocalization of dogs and their emotional aspects. Results of using human behavioral models are very important for autonomous systems, where groups of unmanned robots are set to perform complex tasks, but communication between them is based on human behaviors. In [ 13 ] was discussed how to model a self-organizing strategies for autonomous group of robots in changing environments, while in [ 14 ] these were compared to performance of interactions between working agents. The aim of this project is to show interactions between human and computer. For this reason we have developed a program which presents images to users and measures their choices basing on the category. The program takes the form of a game and selects one of the available images from given field and shows a part of randomly chosen pixels. The number of pixels which are discovered increases with passing time, until all pixels are shown and whole picture is presented. In this time user is asked to guess what in his opinion is presented in the revealed image. In our program we have three available categories: buildings, famous people and animals. Of course, user knows the categories, but he doesn’t see the images in advance. In every field there are 5 pictures, which are selected randomly. In our opinion, such games have a very good effect on people. They examine perceptiveness and knowledge from various fields (eg from geography, history) therefore we have decided to present some research results in this field of human interactions to images.

II. DETAILS OF THE PROGRAM

This project is written in Wolfram Mathematica 10 for research purposes. Now, we talk a bit about the code. In the program, we used the fact that every image can be presented as a pixel’s matrix. The algorithm randomly selects and show from 5% to 50% of pixels of each row with the step 5%. At the last stage the whole picture is exposed. Sample visualization of the process is presented in Fig. 1.

Female Female 40 35 30 25 e im20 T 15 10 5 0

Whole

Male

Female

Buildings

Whole

Male

Female

40 35 30 25

Whole

Male

Female

Whole

Male

Female

The shortest

time [s] 0 4,14567 5,21907

Average time

[s] 17,088236 14,200705 20,42817

The longest

time [s] 35 26,6507 33,4138 Male

Then the image is being exposed with the passing time. When

the user already knows what the picture shows he/she should push “PAUSE”. The part of our code is shown in Fig. 2. The player who correctly guessed with the shortest time wins, but we know that sometimes it is unfair because of the difficulty of the several images. The algorithm is running as long as the matrix is filled with the proper amount of the pixels without duplicates. In each step algorithm works from beginning- it means that it’s not picking the missing quantity of pixels to the matrix from the previous step. The pictures in Fig. 1 show the next stages of the program’s work on a randomly selected image.

III. RESULTS We invited 20 people to play our game. Everyone tried his chances in each category and we received the results presented in Tab. 1 – Tab. 4 and depicted in Fig. 3 – Fig. 7:

For example. The sixth user was woman and the shortest time she obtained was in the category – people. She guessed that in the picture was Marlin Monroe.

It can be observed that during our tests the most often

displayed building was Eiffel Tower, in category people –

Enrique Iglesias and in category animals it was squirrel. The shortest average time needed to guess was for buildings.

Pictures that presented Marlin Monroe and elephant have got the shortest time in their categories.

We can see that differences between man and woman on the

charts visible in Fig. 4 – Fig. 5. In the category buildings, men turned out to be better. In the category people better were women. The smallest differences between men’s and women’s time was in the category animals.

IV. CONCLUSION

Generally men have shorter time than women. Among men, the shortest average time is for pictures from category buildings. While by the decisions all the users were most convenient with images of nature and calm colors, and where the colors were strict and very light these images were not very convenient to users. Sometimes the images were correctly identified in first 5 second due to some explicit details visible in presented objects. On the other hand these were not much visible for people. In general users were correctly recognizing people in images when some facial details appeared and were not able to recognize in first seconds when only a shape was visible.

In our opinion the research gave us important clues how the

people react to various objects. These conclusions will be very useful in our future work, where we can use them for implementing systems oriented communication aspects, where a recognition of the input will be determined by some initial information about the input objects.

References

[1] Kryter , Karl D. "Scaling human reactions to the sound from aircraft." The Journal of the Acoustical Society of America 31.11 ( 1959 ): 1415 - 1429 .

Wilson , Glenn D. , Paul T. Barrett, and Jeffrey A. Gray . "Human reactions to reward and punishment: A questionnaire examination of Gray's personality theory." British Journal of Psychology 80.4 ( 1989 ): 509 - 515 .

Matute , Helena. "Human reactions to uncontrollable outcomes: Further evidence for superstitions rather than helplessness." The Quarterly Journal of Experimental Psychology Section B 48 . 2b ( 1995 ): 142 - 157 .

[4] Lang , Peter J. , et al. "Looking at pictures: Affective, facial, visceral, and behavioral reactions . " Psychophysiology 30.3 ( 1993 ): 261 - 273 .

[5] Beritelli , Francesco, Capizzi, Giacomo, Lo Sciuto, Grazia, Napoli, Christian and Scaglione, Francesco. “ Automatic heart activity diagnosis based on gram polynomials and probabilistic neural networks” . Biomedical Engineering Letters , 8 .1 ( 2018 ): 77 - 85 .

[6] Bradley , Margaret M. , et al. "Emotion and motivation I: defensive and appetitive reactions in picture processing . " Emotion 1 .3 ( 2001 ): 276 .

[7] Platek , Steven M. , et al. "Reactions to children's faces: Resemblance affects males more than females . " Evolution and Human Behavior 23.3 ( 2002 ): 159 - 166 .

[8] Bovet , Dalila, and Jacques Vauclair . "Picture recognition in animals and humans . " Behavioural brain research 109.2 ( 2000 ): 143 - 165 .

[9] Levy , Sidney J . "Dreams, fairy tales, animals, and cars . " Psychology & Marketing 2.2 ( 1985 ): 67 - 81 .

[10] Woźniak , Marcin, Dawid Połap, Christian Napoli , and Emiliano Tramontana . "Application of bio-inspired methods in distributed gaming systems . " Information Technology And Control 46 , no. 1 ( 2017 ): 150 - 164 .

[11] Woźniak , Marcin, and Dawid Połap . "Adaptive neuro-heuristic hybrid model for fruit peel defects detection . " Neural Networks 98 ( 2018 ): 16 - 33 .

[12] Starczewski , Janusz T. , Sebastian Pabiasz , Natalia Vladymyrska, Antonino Marvuglia, Christian Napoli , and Marcin Woźniak . "Self organizing maps for 3D face understanding." In International Conference on Artificial Intelligence and Soft Computing , ( 2016 ): pp. 210 - 217 . Springer.

[13] Woźniak , Marcin , et al. "Automated fluorescence microscopy image analysis of Pseudomonas aeruginosa bacteria in alive and dead stadium . " Engineering Applications of Artificial Intelligence 67 ( 2018 ): 100 - 110 .

[14] Misra , Sanjay , et al. "A Suite of Object Oriented Cognitive Complexity Metrics." IEEE Access ( 2018 ).

[15] Maskeliunas , Rytis, Vidas Raudonis , and Robertas Damasevicius . "Recognition of Emotional Vocalizations of Canine." Acta Acustica united with Acustica 104.2 ( 2018 ): 304 - 314 .

[16] Esmaeili , Ahmad , et al. "A socially-based distributed self-organizing algorithm for holonic multi-agent systems: Case study in a task environment . " Cognitive Systems Research 43 ( 2017 ): 21 - 44 .

[17] Esmaeili , Ahmad , et al. "The impact of diversity on performance of holonic multi-agent systems . " Engineering Applications of Artificial Intelligence 55 ( 2016 ): 186 - 201 .