Background Determining how an image is visually appealing is a complicated and subjective task. This motivates the use of a machine-learning model to evaluate image aesthetics automatically by matching the aesthetics ...Background Determining how an image is visually appealing is a complicated and subjective task. This motivates the use of a machine-learning model to evaluate image aesthetics automatically by matching the aesthetics of the general public. Although deep learning methods have successfully learned good visual features from images,correctly assessing the aesthetic quality of an image remains a challenge for deep learning. Methods To address this, we propose a novel multiview convolutional neural network to assess image aesthetics assessment through color composition and space formation(IAACS). Specifically, from different views of an image––including its key color components and their contributions, the image space formation, and the image itself––our network extracts the corresponding features through our proposed feature extraction module(FET) and the Image Net weight-based classification model. Result By fusing the extracted features, our network produces an accurate prediction score distribution for image aesthetics. The experimental results show that we have achieved superior performance.展开更多
Sea cucumber, Apostichopus japonicus（Selenka）, is a commercially important marine species in China. Among the differently colored varieties sold in China, white and purple sea cucumbers have the greatest appeal to c...Sea cucumber, Apostichopus japonicus（Selenka）, is a commercially important marine species in China. Among the differently colored varieties sold in China, white and purple sea cucumbers have the greatest appeal to consumers. Identification of the pigments that may contribute to the formation of different color morphs of sea cucumbers will provide a scientific basis for improving the cultivability of desirable color morphs. In this study,sea cucumbers were divided into four categories according to their body color： white, light green, dark green, and purple. The pigment composition and contents in the four groups were analyzed by high performance liquid chromatography（HPLC）. The results show that the pigment contents differed significantly among the white, lightgreen, dark-green, and purple sea cucumbers, and there were fewer types of pigments in white sea cucumber than in the other color morphs. The only pigments detected in white sea cucumbers were guanine and pteroic acid.Guanine and pteroic acid are structural colors, and they were also detected in light-green, dark-green, and purple sea cucumbers. Every pigment detected, except for pteroic acid, was present at a higher concentration in purple morphs than in the other color morphs. The biological color pigments melanin, astaxanthin, β-carotene, and lutein were detected in light-green, dark-green, and purple sea cucumbers. While progesterone and lycopene,which are also biological color pigments, were not detected in any of the color morphs. Melanin was the major pigment contributing to body color, and its concentration increased with deepening color of the sea cucumber body. Transmission electron microscopy analyses revealed that white sea cucumbers had the fewest epidermal melanocytes in the body wall, and their melanocytes contained fewer melanosomes as well as non-pigmented pre-melanosomes. Sea cucumbers with deeper body colors contained more melanin granules. In the body wall of dark-green and purple sea cucumbers, melanin granules were secreted out of the cell. The results of this study provide evidence for the main factors responsible for differences in coloration among white, light-green, darkgreen, and purple sea cucumbers, and also provide the foundation for further research on the formation of body color in sea cucumber, A. japonicus.展开更多
Different image processing algorithms have been evaluated in the context of geological mapping using Landsat TM data. False color composites, the principal component imagery, and IHS decorrelation stretching method fo...Different image processing algorithms have been evaluated in the context of geological mapping using Landsat TM data. False color composites, the principal component imagery, and IHS decorrelation stretching method for Landsat-5 TM data have been found useful for delineating the regional geological features, mainly to provide the maximum geological information of the studied area . The study testifies that using which image processing yields best results for geological mapping in arid and semiarid regions by preserving morphological and spectral information. Generally, the studied area can be divided into three main geological units: Basaltic intrusive rocks, Metamorphic with varying intensities and Sedimentary rocks.展开更多
Landsat TM digital spectral data of Lancang Jinghong area (Yunnan P ro vince) has been used for the purpose of geological interpretation. To meet this object, different image processing techniques including selected...Landsat TM digital spectral data of Lancang Jinghong area (Yunnan P ro vince) has been used for the purpose of geological interpretation. To meet this object, different image processing techniques including selected band color comp osites, principal component analysis and IHS decorrelation stretching are used t o improve the discrimination of different lithological and structural features i n the area.It was found that IHS decorrelation stretching images obtained from t he transformation of false color composite 741 (in red, green and blue) prov ided the best results based on the original data.By combining the characteristic s of images produced by different approaches and other canonically transformed i mages with available geological data and surface observations, the geological in terpretation could be done with satisfactory degree of accuracy.展开更多
基金Supported by the National Key R&D Program of China (No:2018YFB1403202)the National Natural Science Foundation of China(62172366)。
文摘Background Determining how an image is visually appealing is a complicated and subjective task. This motivates the use of a machine-learning model to evaluate image aesthetics automatically by matching the aesthetics of the general public. Although deep learning methods have successfully learned good visual features from images,correctly assessing the aesthetic quality of an image remains a challenge for deep learning. Methods To address this, we propose a novel multiview convolutional neural network to assess image aesthetics assessment through color composition and space formation(IAACS). Specifically, from different views of an image––including its key color components and their contributions, the image space formation, and the image itself––our network extracts the corresponding features through our proposed feature extraction module(FET) and the Image Net weight-based classification model. Result By fusing the extracted features, our network produces an accurate prediction score distribution for image aesthetics. The experimental results show that we have achieved superior performance.
基金The Agricultural Seed Project of Shandong Province
文摘Sea cucumber, Apostichopus japonicus（Selenka）, is a commercially important marine species in China. Among the differently colored varieties sold in China, white and purple sea cucumbers have the greatest appeal to consumers. Identification of the pigments that may contribute to the formation of different color morphs of sea cucumbers will provide a scientific basis for improving the cultivability of desirable color morphs. In this study,sea cucumbers were divided into four categories according to their body color： white, light green, dark green, and purple. The pigment composition and contents in the four groups were analyzed by high performance liquid chromatography（HPLC）. The results show that the pigment contents differed significantly among the white, lightgreen, dark-green, and purple sea cucumbers, and there were fewer types of pigments in white sea cucumber than in the other color morphs. The only pigments detected in white sea cucumbers were guanine and pteroic acid.Guanine and pteroic acid are structural colors, and they were also detected in light-green, dark-green, and purple sea cucumbers. Every pigment detected, except for pteroic acid, was present at a higher concentration in purple morphs than in the other color morphs. The biological color pigments melanin, astaxanthin, β-carotene, and lutein were detected in light-green, dark-green, and purple sea cucumbers. While progesterone and lycopene,which are also biological color pigments, were not detected in any of the color morphs. Melanin was the major pigment contributing to body color, and its concentration increased with deepening color of the sea cucumber body. Transmission electron microscopy analyses revealed that white sea cucumbers had the fewest epidermal melanocytes in the body wall, and their melanocytes contained fewer melanosomes as well as non-pigmented pre-melanosomes. Sea cucumbers with deeper body colors contained more melanin granules. In the body wall of dark-green and purple sea cucumbers, melanin granules were secreted out of the cell. The results of this study provide evidence for the main factors responsible for differences in coloration among white, light-green, darkgreen, and purple sea cucumbers, and also provide the foundation for further research on the formation of body color in sea cucumber, A. japonicus.
文摘Different image processing algorithms have been evaluated in the context of geological mapping using Landsat TM data. False color composites, the principal component imagery, and IHS decorrelation stretching method for Landsat-5 TM data have been found useful for delineating the regional geological features, mainly to provide the maximum geological information of the studied area . The study testifies that using which image processing yields best results for geological mapping in arid and semiarid regions by preserving morphological and spectral information. Generally, the studied area can be divided into three main geological units: Basaltic intrusive rocks, Metamorphic with varying intensities and Sedimentary rocks.
文摘Landsat TM digital spectral data of Lancang Jinghong area (Yunnan P ro vince) has been used for the purpose of geological interpretation. To meet this object, different image processing techniques including selected band color comp osites, principal component analysis and IHS decorrelation stretching are used t o improve the discrimination of different lithological and structural features i n the area.It was found that IHS decorrelation stretching images obtained from t he transformation of false color composite 741 (in red, green and blue) prov ided the best results based on the original data.By combining the characteristic s of images produced by different approaches and other canonically transformed i mages with available geological data and surface observations, the geological in terpretation could be done with satisfactory degree of accuracy.
