Research on Simulation System of Rubber Particle Mat Based on Web Technology

The current design of rubber granular floor mats is limited to a single fixed plane sample drawing, and it consumes a lot of time, manpower and material resources in obtaining customer design requirements. In response to this situation, the use of Web development technology to realize the free combination of particles in proportion, generate simulation application scenarios, provide interface operations, and finally complete the order process. By constructing a particle probability distribution model, establishing a particle position coordinate matrix, and developing a particle mat simulation system, based on the sample quality of the sampled data, it is compared with the real artificial mechanical product. Finally, by mixing and matching 9 different color values according to the industrial production ratio, randomly combining 10 groups and comparing with the real products of the same color ratio, quantifying the color difference, contrast, and particle position offset to obtain the production simulation floor mat sample and the actual product. The finished product is quite close. The system generates simulated particle mat maps and real sample maps with a high degree of simulation, and provides an interface that allows users to directly match the particle combination program that suits their needs, saving labor cycles and improving work efficiency.

Color-Ratio Maps Enhanced Optical Filter Design and Its Application in Green Pepper Segmentation

There is a growing demand for developing image sensor systems to aid fruit and vegetable harvesting, and crop growth prediction in precision agriculture. In this paper, we present an end-to-end optimization approach for the simultaneous design of optical filters and green pepper segmentation neural networks. Our optimization method modeled the optical filter as one learnable neural network layer and attached it to the subsequent camera spectral response (CSR) layer and segmentation neural network for green pepper segmentation. We used not only the standard red–green–blue output from the CSR layer but also the color-ratio maps as additional cues in the visible wavelength and to augment the feature maps as the input for segmentation. We evaluated how well our proposed color-ratio maps enhanced optical filter design methods in our collected dataset. We find that our proposed method can yield a better performance than both an optical filter RGB system without color-ratio maps and a raw RGB camera (without an optical filter) system. The proposed learning-based framework can potentially build better image sensor systems for green pepper segmentation.

Geologic Mapping and Age Determinations of Tsiolkovskiy Crater

Tsiolkovskiy is a ~200 km diameter crater presenting one of the few mare deposits of the lunar far side. In this work, we perform a geological study of the crater by means of morpho-stratigraphic and color-based spectral mappings, and a detailed crater counting age determination. The work aims at characterizing the surface morphology and compositional variation observed from orbital data including the Lunar Reconnaissance Orbiter Wide Angle Camera and Clementine UVVIS Warped Color Ratio mosaics, and attempts a reconstruction of the evolutionary history of the Tsiolkovskiy crater through both relative and absolute model age determinations. The results show a clear correlation between the geologic and spectral units and an asymmetric distribution of these units reflecting the oblique impact origin of the crater. Crater counts performed using the spectral units identified on the smooth crater floor returned distinct age ranges, suggesting the occurrence of at least three different igneous events, generating units characterized by particular compositions and/or degree of maturity. This work demonstrates the scientific value of Tsiolkovskiy crater for a better understanding of the volcanic evolution of the Moon and, in particular, of its far side.

A Parallel Partial Enhancement Method for License Plate Localization in Low-Quality Images

Finding an effective license plate localization (LPL) method is challenging owing to different conditions during the image acquisition phase. Most existing methods do not consider various low-quality image conditions that exist in real-world situations. Low-quality image conditions mean that an image can have low resolution, plate imperfection effects, variable illumination environments or background objects similar to the license plate (LP). To improve the anti-interference ability and the speed performance of algorithm, this study aims to develop a parallel partial enhancement method based on color differences that demonstrates improved localization performance for blue–white LP images under low-quality conditions. A novel color difference model is exploited to enhance LP areas and filter non-LP areas. Blue–white color ratio and projection analysis are performed to select the exact LP area from the candidates. Moreover, this study develops a parallel version based on a multicore CPU for real-time processing for industrial applications. An image database including 395 low-quality car images captured from various scenes under different conditions is tested for the performance evaluation. The extensive experiments show the effectiveness and efficiency of the proposed approach.

THERMAL INFLUENCE ON THE SURFACE INTEGRITY DURING SINGLE-LIP DEEP HOLE DRILLING OF STEEL COMPONENTS

The thermomechanical load on the workpiece surface during the machining process strongly influences its surface integrity and the resulting fatigue strength of the components. In single-lip drilling, the measurement of the mechanical load using dynamometers is well established, but the thermal interactions between the tool and the workpiece material in the surface area are difficult to determine with conventional test setups. In this paper, the development and implementation of an in-process measurement of the thermal load on the bore subsurface is presented. The experimental setup includes a two-color ratio pyrometer in combination with thermocouples, which enable temperature measurement on the tool’s cutting edge as well as in the bore subsurface. In combination, a force measurement dynamometer for measuring the occurring force and torque is used. Thus, the influence of different cutting parameter variations on the thermomechanical impact on the bore surface can be evaluated.

Optical sensing of chlorophyll(in) with dual-spectrum Si LEDs in SOI CMOS technology

Small and low-cost chlorophyll sensors are popular in agricultural sector and food-quality control. Combining such sensors with silicon CMOS electronics is challenged by the absence of silicon-integrated light-sources. We experimentally achieve optical absorption sensing of chlorophyll based pigments with silicon (Si) micro light-emitting diodes (LED) as light-source, fabricated in a standard SOI-CMOS technology. By driving a Si LED in both forward and avalanche modes of operation, we steer its electroluminescent spectrum between visible (400–900 nm) and near-infrared (~1120 nm). For detection of chlorophyll in solution phase, the dual-spectrum light from the LED propagates vertically through glycerol micro-droplets containing sodium copper chlorophyllin at varying relative concentrations. The transmitted light is detected via an off-chip Si photodiode. The visible to near-infrared color ratio (COR) of the photocurrent yields the effective absorption coefficient. We introduce the LED-specific molar absorption coefficient as a metric to compute the absolute pigment concentration (?~0.019 ?M) and validate the results by measurements with a hybrid spectrophotometer. With the same sensor, we also show non-invasive monitoring of chlorophyll in plant leaves. COR sensitivities of ? 3.9? x 10⁴ M^-1 and ? 5.3? x 10⁴ M^-1 are obtained for two leaf species, where light from the LED propagates diffusely through the thickness of the leaf prior to detection by the photodiode. Our work demonstrates the feasibility of realizing fully CMOS-integrated optical sensors for biochemical analyses in food sector and plant/human health.

Optical sensing of chlorophyll(in) with dual-spectrum Si LEDs in SOI CMOS technology

Small and low-cost chlorophyll sensors are popular in agricultural sector and food-quality control. Combining such sensors with silicon CMOS electronics is challenged by the absence of silicon-integrated light-sources. We experimentally achieve optical absorption sensing of chlorophyll based pigments with silicon (Si) micro light-emitting diodes (LED) as light-source, fabricated in a standard SOI-CMOS technology. By driving a Si LED in both forward and avalanche modes of operation, we steer its electroluminescent spectrum between visible (400–900 nm) and near-infrared (~1120 nm). For detection of chlorophyll in solution phase, the dual-spectrum light from the LED propagates vertically through glycerol micro-droplets containing sodium copper chlorophyllin at varying relative concentrations. The transmitted light is detected via an off-chip Si photodiode. The visible to near-infrared color ratio (COR) of the photocurrent yields the effective absorption coefficient. We introduce the LED-specific molar absorption coefficient as a metric to compute the absolute pigment concentration (?~0.019 ?M) and validate the results by measurements with a hybrid spectrophotometer. With the same sensor, we also show non-invasive monitoring of chlorophyll in plant leaves. COR sensitivities of ? 3.9? x 10⁴ M^-1 and ? 5.3? x 10⁴ M^-1 are obtained for two leaf species, where light from the LED propagates diffusely through the thickness of the leaf prior to detection by the photodiode. Our work demonstrates the feasibility of realizing fully CMOS-integrated optical sensors for biochemical analyses in food sector and plant/human health.

Raman spectroscopy, mobility size and radiative emissions data for soot formed at increasing temperature and equivalence ratio in flames hotter than conventional combustion applications

The dataset presented in this article is linked to the research article titled “Evolution in size and structural order for incipient soot formed at flame temperatures greater than 2100 K” [1]. The research article discusses the systematic evolution of flame formed carbon in premixed stagnation flames with flame temperatures hotter than conventional combustion applications. The effect of the growth environment on particle size, structure, composition and properties are studied. The flame temperature (1950 K < Tf,max < 2250 K) and equivalence ratio (Φ = 2.4, 2.5, and 2.6) are methodically varied to analyze impact on insipient soot while maintaining a comparable particle residence time (tp ~ 15 ms). This article presents the data acquired for this systematic study. The data presented herein provides fundamental observations suitable for development of soot formation theory and modeling. Characterization of material properties and morphology are also relevant to potential applications of functional carbon nanomaterials. Raman spectra are measured for carbon films deposited from the flames, soot particle size distributions are obtained by aerosol sampling from the flames and soot radiative emissions are measured in-situ by color-ratio pyrometry. Deconvolution of Raman peaks is carried out to extract information on carbon bonding and structural order. Flame temperature is extracted from the measured color-ratio field making assumptions for the soot optical dispersion exponent.

Main color extraction algorithm and its application in clothing image retrieval

In content-based clothing image retrieval, color features can best reflect the basic characteristics of clothing, and also the most stable visual features. Compared with other image features, color features have smaller size, orientation and visual dependence. This paper studies the application of dominant color extraction algorithm in clothing image retrieval, and proposes a clothing classification method based on dominant color ratio. Clothing image is divided into color clothing and non color clothing. On this basis, a main color extraction algorithm of clothing image color feature extraction is proposed. Taking the clothing color features as an example, the image features are analyzed, and then the SVM image classification algorithm is designed to analyze the image features. Then an improved scheme based on data mining technology is proposed, and the analysis model based on association rules is established. Finally, a method of standard man hour correction based on association rules is proposed. The experimental results show that, compared with the existing algorithms, the recall rate and accuracy rate are significantly improved for the clothing with simple or complex background, pattern and non pattern clothing. Analyze and divide the specific areas of clothing image, extract the main color of clothing image, share and recommend clothing image and color extraction results. This research not only has certain research significance, but also has certain practical application value.