A computational creativity approach from music to images

2021 ◽  
Vol 14 (2) ◽  
pp. 1-5
Author(s):  
Luís Aleixo H. Sofía Pinto ◽  
Nuno Correia
Keyword(s):  
Genetic Algorithm ◽  
Creative Process ◽  
Sound Art ◽  
Color Theory ◽  
Computational Creativity ◽  
Online Surveys ◽  
Art And Design ◽  
Cross Domain ◽  
Visual Characteristics ◽  
Aesthetic Preferences

Our system generates abstract images from music that serve as inspiration for the creative process. We developed one of many possible approaches for a cross-domain association between the musical and visual domains, by extracting features from MIDI music files and associating them to visual characteristics. The associations were led by the authors' aesthetic preferences and some experimentation. Three different approaches were pursued, two with direct or random associations and a third using a genetic algorithm that considers music and color theory while searching for better results. The resulting images were evaluated through online surveys, which confirmed that not only they were abstract, but also that there was a relationship with the music that served as the basis for the association process. Moreover, the majority of the participants ranked highest the images improved with the genetic algorithm. This newsletter contribution summarizes the full version of the article, which was presented at EvoMUSART 2021 (the 10th International Conference on Artificial Intelligence in Music, Sound, Art and Design).

scholarly journals The Artistry and Creative Process in the Making of Malang Masks in East Java | Kesenian dan Proses Kreatif dalam Penciptaan Topeng Malang di Jawa Timur

SPAFA Journal ◽  
2021 ◽  
Vol 5 ◽  
Author(s):  
Guntur [n/a]
Keyword(s):  
Creative Process ◽  
Cultural Background ◽  
Qualitative Description ◽  
Facial Appearance ◽  
Unique Form ◽  
Common People ◽  
The Common ◽  
Visual Characteristics ◽  
Unique Style ◽  
And Function

The creative process in Malang mask making has a strong tradition of creation which has produced a unique form. The Malang mask art has been popularized based on the Panji story. Despite being properties of an art performance, the masks are works of art. The visual characteristics of the faces and their carved ornaments are the main elements that determine the typology of the mask’s facial appearance. The characteristics of form, color, expression, and function create a unique style or identity of the group of traditional mask artists in Malang. Masks can be classified according to four general types of character: the figure of Panji, antagonistic characters, servants, and animals. In terms of the traditionality of creation, including aspects of material, technique, and function in the community of craftsmen, the style of the masks refers to previously existing forms. This essay is a qualitative description of the artistry of Malang masks, through the formation of the Panji story – based on kidung as indigenous stories in the practice of adaptive Hinduism – and leaning on a dichotomy with the Kakawin form. Malang masks are used by the wayang topeng community in art performances to present the narration of the Panji story – against the spiritual cultural background of the common people. Process kreatif dalam pembuatan topeng Malang memiliki tradisi penciptaan yang kuat, dan telah menghasilkan bentuk yang khas. Topeng Malang dipopulerkan berdasarkan kisah Panji. Meskipun menjadi properti seni pertunjukan, topeng adalah karya seni. Karakteristik visual wajah dan ornamen ukir merupakan elemen utama yang membentuk tipologi perwajahan topeng. Karakteristik pada bentuk, warna, ekspresi, serta fungsi, menghasilkan gaya atau identitas unik dari kelompok seniman topeng tradisional di Malang. Klasifikasi topeng ada pada empat tipologi umum karakter tokoh: sosok Panji, tokoh antagonis, tokoh abdi, dan tokoh binatang. Dari sisi tradisionalitas penciptaan, yaitu aspek materialitas, teknik, dan fungsinya di komunitas perajin, gaya topeng mengacu kepada bentuk topeng yang ada sebelumnya. Esai ini mendeskripsikan secara kualitatif perwujudan artistik topeng Malang, melalui formasi kisah Panji - berdasarkan kidung sebagai cerita asli dalam praktek Hinduisme adaptif - dan bersandar pada dikotomi dengan bentuk Kakawin. Topeng Malang digunakan oleh masyarakat topeng wayang dalam pertunjukan seni untuk menampilkan narasi kisah Panji - dengan latar belakang kultural spiritual orang biasa.

The Overheard: An Attuning Approach to Sound Art and Design in Public Spaces

2021 ◽  
Author(s):  
Marie Højlund ◽  
Jonas R. Kirkegaard ◽  
Michael Sonne Kristensen ◽  
Morten Riis
Keyword(s):  
Public Spaces ◽  
Sound Art ◽  
Art And Design

scholarly journals The Ubiquity of Cross-Domain Thinking in the Early Phase of the Creative Process

2019 ◽  
Vol 10 ◽  
Author(s):  
Victoria S. Scotney ◽  
Sarah Weissmeyer ◽  
Nicole Carbert ◽  
Liane Gabora
Keyword(s):  
Creative Process ◽  
Early Phase ◽  
Cross Domain

scholarly journals Robustious Feature Selection Based Genetic Algorithm (RFS-GA) For Cross Domain Opinion Mining

2019 ◽  
Vol 8 (2) ◽  
pp. 6267-6279
Keyword(s):  
Genetic Algorithm ◽  
Feature Selection ◽  
Sentiment Analysis ◽  
Opinion Mining ◽  
Performance Metrics ◽  
Research Work ◽  
Features Selection ◽  
Cross Domain ◽  
Multiple Challenges ◽  
Day By Day

Day by day the requirement of information for processing the sentiment analysis is getting increased multiple times. For these kind of reasons, feature selection is utilized to detect the opinion among different reviews and comments. Sentiment analysis is becoming like phenomenon due to increase of social media’s popularity. Currently, significant advancements are shown in this research domain, but still multiple challenges are to be solved – i.e., sentiment analysis in cross domains. In this paper rumbustious feature selection based genetic algorithm is proposed to address the problem of analyzing the sentiments in cross domain. It performs classification based optimistic-class and pessimistic-class. The dataset used to this research work includes books, DVDs, gadgets and kitchen appliances. Initially the features selection is performed and opinion mining is performed by Genetic Algorithm. Benchmark performance metrics are selected for measuring the performance of proposed work against existing method. Results depict that the proposed work has better performance than that of the existing work as far as chosen performance metrics.

scholarly journals Generating Creative Language - Theories, Practice and Evaluation

2020 ◽  
Author(s):  
Mika Hämäläinen
Keyword(s):  
Genetic Algorithm ◽  
Natural Language ◽  
Ad Hoc ◽  
Theoretical Perspective ◽  
Theoretical Work ◽  
Computational Creativity ◽  
Practical Solution ◽  
Language Generation ◽  
Communicative Context ◽  
Creative Language

This thesis presents approaches to computationally creative natural language generation focusing on theoretical foundations, practical solutions and evaluation. I defend that a theoretical definition is crucial for computational creativity and that the practical solution must closely follow the theoretical definition. Finally, evaluation must be based on the underlying theory and what was actually modelled in the practical solution. A theoretical void in the existing theoretical work on computational creativity is identified. The existing theories do not explicitly take into account the communicative nature of natural language. Therefore, a new theoretical framework is elaborated that identifies how computational creativity can take place in a setting that has a clear communicative goal. This introduces a communicative-creative trade off that sets limits to creativity in such a communicative context. My framework divides creativity in three categories: message creativity, contextual creativity and communicative creativity. Any computationally creative NLG approach not taking communicativity into account is called mere surface generation.I propose a novel master-apprentice approach for creative language generation. The approach consists of a genetic algorithm, the fitness functions of which correspond to different parameters defined as important for the creative task in question from a theoretical perspective. The output of the genetic algorithm together with possible human authored data are used to train the apprentice, which is a sequence-to-sequence neural network model. The role of the apprentice in the system is to approximate creative autonomy.Evaluation is approached from three different perspectives in this work: ad-hoc and abstract, theory-based and abstract, and theory-based and concrete. The first perspective is the most common one in the current literature and its shortcomings are demonstrated and discussed. This starts a gradual shift towards more meaningful evaluation by first using proper theories to define the task being modelled and finally reducing the room for subjective interpretation by suggesting the use of concrete evaluation questions.

Sign in / Sign up

Export Citation Format

Share Document