The hybridoma cell screening method is usually done manually by human eyes during the production process for monoclonal antibody drugs. This traditional screening method has certain limitations, such as low efficiency and subjectivity bias. Furthermore, most of the existing deep learning-based image segmentation methods have certain drawbacks, due to different shapes of hybridoma cells and uneven location distribution. In this paper, we propose a deep hybridoma cell image segmentation method based on residual and attention U-Net (RA-UNet). Firstly, the feature maps of the five modules in the network encoder are used for multi-scale feature fusion in a feature pyramid form and then spliced into the network decoder to enrich the semantic level of the feature maps in the decoder. Secondly, a dual attention mechanism module based on global and channel attention mechanisms is presented. The global attention mechanism (non-local neural network) is connected to the network decoder to expand the receptive field of the feature map and bring more rich information to the network. Then, the channel attention mechanism SENet (the squeeze-and-excitation network) is connected to the non-local attention mechanism. Consequently, the important features are enhanced by the learning of the feature channel weights, and the secondary features are suppressed, hence improving the cell segmentation performance and accuracy. Finally, the focal loss function is used to guide the network to learn the hard-to-classify cell categories. Furthermore, we evaluate the performance of the proposed RA-UNet method on a newly established hybridoma cell image dataset. Experimental results show that the proposed method has good reliability and improves the efficiency of hybridoma cell segmentation compared with state-of-the-art networks such as FCN, UNet, and UNet++. The results show that the proposed RA-UNet model has improvements of 0.8937%, 0.9926%, 0.9512%, and 0.9007% in terms of the dice coefficients, PA, MPA, and MIoU, respectively.

Image generative models for ceramic tile design lack style diversity and controllability of high-quality generated styles. It is difficult to find a series of ceramic tiles with the same texture but distinct styles, that makes it a challenging for users to select from a limited number of tiles with a single style. Although, Generative Adversarial Networks (GANs) can slightly increase the style diversity of tile images, the style controllability remains very weak. Additionally, concatenating generated tile image blocks to obtain a larger texture region can easily result in seams at the boundaries that decrease image quality. In this paper, we propose a style transfer method for ceramic tiles texture generation that combines a classifier-guided StyleGAN with AdaIN-GAN to overcome the above limitations. Firstly, we introduce a new conditional classifier-guided module into the StyleGAN. With the guidance of the input condition vector, the output image is made to have the tile style characteristics that match the vector. At the same time, the fusion of the condition vectors realizes the style gradient effect of the tile image to expand the style diversity. Secondly, we use the AdaIN-GAN to color the original texture in tile style. The style images generated by StyleGAN are then used as a dataset for model training to enhance the generalization ability of the model and achieve a style transfer effect with fixed texture features but significantly diverse styles. Finally, a linear weighted image stitching method is adopted, which uses an adaptive kernel linear weighted matrix to cover and splice arbitrary seams with image blocks, thereby successfully eliminating seams and enhancing image continuity. When this method is applied to high-resolution tile image generation, the method still maintains higher continuity and clearer image quality. Extensive experiments and human evaluation confirm the superior performance of the proposed method compared with other SOTA methods. The experimental results also verify that the new tile images generated by the proposed algorithm have diverse styles and meet the design requirements for tile style diversity.

Deep learning techniques have been recently widely used in the field of texture image generation. There are still two major problems when applying them to tile image design work. On the one hand, there is still lack of enough diverse ceramic tile images for the training process. On the other hand, the output image is difficult to control and adjust, and cannot meet the designer’s requirements of interactivity. Therefore, we propose a multi-stage generation algorithm of tile images based on generative adversarial network(GAN). First, the multi-scale attention GAN is applied to generate controllable texture image. Then, the SWAG texture synthesis GAN is also applied to obtain controllable and diverse image style. And finally, through the style iteration mechanism and the multiple step magnification method based on image super-resolution reconstruction network, the final tile images can be automatically generated with larger-size and higher-precision. The relevant experiments demonstrate that our method can not only generate high-quality tile images in a relatively short period of time, but also consider human interaction to a certain extent, and maintain a certain degree of control over the main texture and style of the final generated tile images. It has good and wide application value.