Organisms with active camouflage ability exhibit changeable appearance with the switching of environments. However, manmade active camouflage systems heavily rely on integrating electronic devices, which encounters problems including a complex structure, poor usability, and high cost . In the current work, we report active camouflage as an intrinsic function of materials by proposing self-adaptive photochromism (SAP). The SAP materials were fabricated using donor-acceptor Stenhouse adducts (DASAs) as the negative photochromic phases and organic dyes as the fixed phases (nonphotochromic). Incident light with a specific wavelength induces linear -to- cyclic isomerization of DASAs, which generates an absorption gap at the wavelength and accordingly switches the color. The SAP materials are in the primary black state under dark and spontaneously switch to another color upon triggering by transmitted and reflected light in the background. SAP films and coatings were fabricated by incorporating polycaprolactone and are applicable to a wide variety of surfaces.

The representation of physical characteristics is the most essential feature of mathematical models used for the detection of defects in automatic inspection systems. However, the feature of defects and formation of the defect image are not considered enough in traditional algorithms. This paper presents a mathematical model for defect inspection, denoted as the localized defects image model (LDIM), is different because it modeling the features of manual inspection, using a local defect merit function to quantify the cost that a pixel is defective. This function comprises two components: color deviation and color fluctuation. Parameters related to statistical data of the background region of images are also taken into consideration. Test results demonstrate that the model matches the definition of defects, as defined by international industrial standards IPC-A-610D and IPC-A-600G. Furthermore, the proposed approach enhances small defects to improve detection rates. Evaluation using a defects images database returned a 100% defect inspection rate with 0% false detection. Proving that this method could be practically applied in manufacture to quantify inspection standards and minimize false alarms resulting from human error

Phase unwrapping is a critical step to obtaining a continuous phase distribution in optical phase measurements and coherent imaging techniques. Traditional phase-unwrapping methods are generally low performance due to significant noise or undersampling. This paper proposes a deep convolutional neural network (DCNN) with a weighted jump-edge attention mechanism, namely, VDE-Net, to realize effective and robust phase unwrapping. Experimental results revealed that the weighted jump-edge attention mechanism, which is first proposed and simple to calculate, is useful for phase unwrapping. The proposed algorithm outperformed other networks or common attention mechanisms. In addition, an unseen wrapped phase image of a living red blood cell (RBC) was successfully unwrapped by the trained VDE-Net, thereby demonstrating its strong generalization capability.

Automatic identification of fungi in microscopic fecal images provides important information for evaluating digestive diseases. To date, disease diagnosis is primarily performed by manual techniques. However, the accuracy of this approach depends on the operator’s expertise and subjective factors. The proposed system automatically identifies fungi in microscopic fecal images that contain other cells and impurities under complex environments. We segment images twice to obtain the correct area of interest, and select ten features, including the circle number, concavity point, and other basic features, to filter fungi. An artificial neural network (ANN) system is used to identify the fungi. The first stage (ANN-1) processes features from five images in differing focal lengths; the second stage (ANN-2) identifies the fungi using the ANN-1 output values. Images in differing focal lengths can be used to improve the identification result. The system output accurately detects the image, whether or not it has fungi. If the image does have fungi, the system output counts the number of different fungi types.

Identifying fungi in microscopic leucorrhea images provides important information for evaluating gynecological diseases. Subjective judgment and fatigue can greatly affect recognition accuracy. This paper proposes an automatic identification system to detect fungi in leucorrhea images that incorporates a convolutional neural network, the histogram of oriented gradients algorithm, and a binary support vector machine. In experiments, the detection rate of the positive samples was as high as 99.8%. The experimental results demonstrate the effectiveness of the proposed method and its potential as a primary software component of a completely automated system.