With the rise of labor costs and the advancement of automation in the textile industry, fabric defect detection has become a hot research field in recent years. We proposed a learning-based framework for automatic detection of fabric defects. Firstly, we use a fixed-size square slider to crop the original image to a certain step and regularity. Then an improved histogram equalization is used to enhance each cropped image. Furthermore, the Inception-V1 model is employed to predict the existence of defects in the local area. Finally, we apply the LeNet-5 model, which plays the role of a voting model, to recognize the type of the defect in the fabric. In brief, the proposed framework mainly consists of two steps, namely local defect prediction and global defect recognition. Experiments on the dataset have demonstrated the superior performance in fabric defect detection.

With the development of perceptual consumption, consumers sometimes cannot explicitly describe the purchase demands or only based on impression, like the color perception and aesthetic experience. Based on the consumer's expression, it is difficult to design a new fabric by repeated proofing to meet the consumer's demands. To retrieve the existing patterns incorporating human intuition and emotion, this study proposed a novel pattern retrieval method of yarn-dyed plaid fabric using modified interactive genetic algorithm. Each pattern was encoded based on the design elements and visual features were extracted to bridge the semantic gap between the designer and the consumer. Survival of the fittest and two special mutation operators, addition and deletion, were designed to increase the diversity of the generations. During the evolution, the generated patterns were replaced by the most similar patterns in the database based on visual features. Experimental results showed that the proposed scheme is feasible and effective to extract the consumer's preferences and retrieve satisfactory patterns, helping the factory obtain the process sheet to guide production and save labor and material resources.

The loss properties of semiconductor laser beams propagating in hollow waveguides (HWGs) are crucial in several applications. The attenuation coefficient of the distributed feedback quantum cascade laser (DFB-QCL) in the HWG was quantitatively determined by measuring its beam profile and laser power along the length of the HWG. The experimental reliability was evaluated, with measurement uncertainties as low as 2.6% and 0.5% for the full width at half maximum (FWHM) of beam profile and the laser power, respectively. We derived an empirical formula for the attenuation coefficient, which is exponential rather than linear with the length of the HWG. The formula was verified to be highly accurate, with a 76.2% reduction in deviation compared to the data in the datasheet. We propose a new concept for a free optical path (FOP) that depends on the inner diameter of the HWG and the incident angle of the beam. The FOP could be an excellent parameter for designing or optimizing HWG-based sensors.

This paper presents a mid-infrared dimethyl sulfide (CH3SCH3, DMS) sensor based on tunable laser absorption spectroscopy with a distributed feedback interband cascade laser to measure DMS in the atmosphere. Different from previous work, in which only DMS was tested and under pure nitrogen conditions, we measured DMS mixed by common air to establish the actual atmospheric measurement environment. Moreover, we used tunable laser absorption spectroscopy with spectral fitting to enable multi-species (i.e., DMS, CH4, and H2O) measurement simultaneously. Meanwhile, we used empirical mode decomposition and greatly reduced the interference of optical fringes and noise. The sensor performances were evaluated with atmospheric mixture in laboratory conditions. The sensor’s measurement uncertainties of DMS, CH4, and H2O were as low as 80 ppb, 20 ppb, and 0.01% with an integration time 1 s, respectively. The sensor possessed a very low detection limit of 9.6 ppb with an integration time of 164 s for DMS, corresponding to an absorbance of 7.4 × 10−6, which showed a good anti-interference ability and stable performance after optical interference removal. We demonstrated that the sensor can be used for DMS measurement, as well as multi-species atmospheric measurements of DMS, H2O, and CH4 simultaneously.

No abstract

In this article, an intelligent inspection method based on image analysis is proposed to identify the color and woven pattern of yarn-dyed fabric automatically. The local sequence images under the reflected light and transmitted light (LSRT images), which consist of reflection sequence images and transmission sequence images, are first captured by a fabric image acquisition device. Then the Fourier transform, image segmentation, and arithmetic operations are employed to the transmission sequence images to determine the location of weave points. Subsequently, the L*a*b* values of each weave point are extracted from the reflection sequence images. To inspect the color pattern, X-means clustering algorithm is used to classify the weave points based on the L*a*b* values. To detect the woven pattern, incomplete weave pattern matrixes of all sequence images are used to match the weave pattern database. Eight LSRT images of each yarn-dyed fabric sample are tested by the proposed method. The experimental results proved that the proposed method can recognize the color and weave pattern of yarn-dyed fabric with satisfactory accuracy and good robustness.

No abstract

Imprecise measurements present universally due to variability in the measurement error. We devised a very simple membership function to evaluate fuzzily the quality of optical sensing with a small dataset, where a normal distribution cannot be assumed. The proposed membership function was further used as a weighting function for non-linear curve fitting under expected mathematical model constraints, namely the membership function-weighted Levenberg–Marquardt (MFW-LM) algorithm. The robustness and effectiveness of the MFW-LM algorithm were demonstrated by an optical-sensing simulation and two practical applications. (1) In laser-absorption spectroscopy, molecular spectral line modeling was greatly improved by the method. The measurement uncertainty of temperature and pressure were reduced dramatically, by 53.3% and 43.5%, respectively, compared with the original method. (2) In imaging, a laser beam-profile reconstruction from heavy distorted observations was improved by the method. As the dynamic range of the infrared camera increased from 256 to 415, the detailed resolution of the laser-beam profiles increased by an amazing 360%, achieving high dynamic-range imaging to capture optical signal details. Therefore, the MFW-LM algorithm provides a robust and effective tool for fitting a proper physical model and precision parameters from low-quality data.