Gentropy: evolving 2D textures

Wiens, Andrea L.; Ross, Brian J.

doi:10.1016/s0097-8493(01)00159-5

Cited by 38 publications

(21 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The system attempted to replicate image characteristics of a target image by performing wavelet analysis. Wiens and Ross's Gentropy [57] used an unsupervised approach, where a target texture image represents the desired texture features, such as colour, shape, and smoothness (contrast). Then the system evolves textures without any user interaction.…”

Section: Evolutionary Artmentioning

confidence: 99%

Deep Learning Concepts for Evolutionary Art

Tanjil

Ross

2019

Computational Intelligence in Music, Sound, Art and Design

Self Cite

View full text Add to dashboard Cite

A deep convolutional neural network (CNN) trained on millions of images forms a very high-level abstract overview of any given target image. Our primary goal is to use this high-level content information of a given target image to guide the automatic evolution of images. We use genetic programming (GP) to evolve procedural textures.We incorporate a pre-trained deep CNN model into the fitness. We are not performing any training, but rather, we pass a target image through the pre-trained deep CNN and use its the high-level representation as the fitness guide for evolved images. We develop a preprocessing strategy called Mean Minimum Matrix Strategy (MMMS) which reduces the dimensions and identifies the most relevant high-level activation maps. The technique using reduced activation matrices for a fitness shows promising results. GP is able to guide the evolution of textures such that they have shared characteristics with the target image. We also experiment with the fully connected "classifier" layers of the deep CNN. The evolved images are able to achieve high confidence scores from the deep CNN module for some tested target images. Finally, we implement our own shallow convolutional neural network with a fixed set of filters.Experiments show that the basic CNN had limited effectiveness, likely due to the lack of training. In conclusion, the research shows the potential for using deep learning concepts in evolutionary art. As deep CNN models become better understood, they will be able to be used more effectively for evolutionary art.

show abstract

Section: Evolutionary Artmentioning

confidence: 99%

Deep Learning Concepts for Evolutionary Art

Tanjil

Ross

2019

Computational Intelligence in Music, Sound, Art and Design

Self Cite

View full text Add to dashboard Cite

show abstract

“…Small differences sometimes provide visually interesting 'stylistic' variations on the target image. Examples of this approach are seen in Gentropy (Wiens and Ross, 2002), and in Alsing (2008). Hertzmann (2001) used a similar approach based on relaxation.…”

Section: Related Workmentioning

confidence: 99%

Evolving textures from high level descriptions

Reynolds

2016

IJART

View full text Add to dashboard Cite

Evolutionary texture synthesis is used in a prototype tool intended to assist a designer or artist by automatically discovering collections of candidate textures to fit a given stylistic description. The textures used here are small colour images created by procedural texture synthesis. This paper describes four examples of stylistic description. Each is defined by a handwritten fitness function that rates how well a given texture meets this style. Genetic programming uses the fitness function to evolve programs written in a texture synthesis language. This system automatically generates a catalogue of variations on the given theme. A designer could then visually scan through these textures to pick out ones that seem aesthetically interesting. Their procedural 'genetic' representation would allow textures to be further adjusted by interactive evolution. The procedural representation also allows re-rendering textures at arbitrary pixel resolutions and provides a way to store them in a highly compressed form allowing lossless reconstruction.

show abstract

“…The four co-occurrence based features are contrast, entropy, inverse difference moment and correlation with displacements d = 2,4,6 and 8 along directions φ = 0 and 90 degrees. This produces 4 × 4 × 2 = 32 co-occurrence based features of the image B k .The autocorrelation coefficients are computed with eight displacements (0,2),(0,4),(0,6),(0,8), (2,0),(4,0), (6,0) and (8,0). This provides eight auto-correlation coefficients.…”

Section: Computation Of Featuresmentioning

confidence: 99%

“…Consequently some methods generate textures similar to a(or a set of) given reference texture(s). This type of GP based schemes are presented in [8] which evolve procedures to produce textures similar to a given reference texture. This is an interesting approach but requires reference texture(s) and also produced only similar textures with respect to the given reference texture(s).…”

Section: Introductionmentioning

confidence: 99%

Texture Generation for Fashion Design Using Genetic Programming

Muni

Pal

Das

2006

2006 9th International Conference on Control, Automation, Robotics and Vision

View full text Add to dashboard Cite

We present a methodology to generate textures for fashion design using Genetic Programming(GP). The proposed GP based scheme evolves tree representation of procedures to generate textures. We use Contrast of the generated textures/images to filter out poor textures. After filtering, the fitness value of a new texture is set as the fitness value of a cluster of (already generated) textures which is more similar to this new texture. For this, we execute a clustering step during the evolution. Statistical features are used to find the similarity between textures. Since the quality of a texture is best assessed by a human being, if the generated texture is quite dissimilar to the existing textures then user's discretion is sought to assign a fitness value to it by visual inspection of the texture.

show abstract

Gentropy: evolving 2D textures

Cited by 38 publications

References 5 publications

Deep Learning Concepts for Evolutionary Art

Deep Learning Concepts for Evolutionary Art

Evolving textures from high level descriptions

Texture Generation for Fashion Design Using Genetic Programming

Contact Info

Product

Resources

About