基于颜色名和OpponentSIFT特征的鳞翅目昆虫图像识别

【目的】本研究旨在探索使用先进的计算机视觉技术实现对昆虫图像的自动分类方法。【方法】通过预处理对采集的昆虫标本图像去除背景,获得昆虫图像的前景蒙板,并由蒙板确定的轮廓计算出前景图像的最小包围盒,剪切出由最小包围盒确定的前景有效区域,然后对剪切得到的图像进行特征提取。首先提取颜色名特征,把原来的RGB（Red-Green-Blue）图像的像素值映射到11种颜色名空间,其值表示RGB值属于该颜色名的概率,每个颜色名平面划分成3×3像素大小的网格,用每格的概率均值作为网格中心点的描述子,最后用空阈金字塔直方图统计的方式形成颜色名视觉词袋特征;其次提取Opponent SIFT（Opponent Scale Invariant Feature Transform）特征,首先把RGB图像变换到对立色空间,对该空间每通道提取SIFT特征,最后用空域池化和直方图统计方法形成Opponent SIFT视觉词袋。将两种词袋特征串接后得到该昆虫图像的特征向量。使用昆虫图像样本训练集提取到的特征向量训练SVM（Support Vector Machine）分类器,使用这些训练得到的分类器即可实现对鳞翅目昆虫的分类识别。【结果】该方法在包含10种576个样本的昆虫图像数据库中进行了测试,取得了100%的识别正确率。【结论】试验结果证明基于颜色名和Opponent SIFT特征可以有效实现对鳞翅目昆虫图像的识别。

Performance evaluation of wavelet scattering network in image texture classification in various color spaces

The optimized color space is searched by using the wavelet scattering network in the KTH_TIPS_COL color image database for image texture classification. The effect of choosing the color space on the classification accuracy is investigated by converting red green blue （RGB） color space to various other color spaces. The results show that the classification performance generally changes to a large degree when performing color texture classification in various color spaces, and the opponent RGB-based wavelet scattering network outperforms other color spaces-based wavelet scattering networks. Considering that color spaces can be changed into each other, therefore, when dealing with the problem of color texture classification, converting other color spaces to the opponent RGB color space is recommended before performing the wavelet scattering network.

电力巡线无人机航拍图像拼接算法

针对电力巡线无人机挂载相机的画幅过小,不能拍摄全局电力线图像等问题,提出一种基于局部特征的电力线图像拼接算法。利用AKAZE算法提取特征点和主方向;根据特征点所在尺度建立Opponent对立色彩空间和Opponent-MLDB二进制描述符;借助尽可能投影变换配准模型,对目标图像投影变换配准,加权叠加融合图像。实验表明:该算法的特征点匹配正确率比现有的匹配算法稳定性更强,拼接效果良好,无明显拼接痕迹。

改进FAST和对立颜色特征的向量场一致性匹配

针对目前传统图像匹配算法在复杂环境下存在误匹配点对过多、稳健性较差等问题,本文提出一种基于改进FAST的特征点提取,结合对立颜色特征的图像匹配算法。首先,利用改进FAST算法提取的角点作为特征点,结合改进的Opponent SIFT算法对特征点进行描述;然后,使用基于字符定位算法对提取的特征点对进行粗匹配,降低整体匹配过程中特征点对误匹配的风险。最后,为了规避因RANSAC算法易陷入局部最优解而导致正确点对被误剔除的问题,运用向量场一致性替代RANSAC进行提纯,降低误匹配率。通过对比试验表明,改进算法匹配准确率均大于91%,且对差异变化具有较好的稳健性、适应性。

Automatic Quality Inspection of Bakery Products Based on Shape and Color Information

An automatic intelligent system for the colour and texture inspection of bakery products is proposed.In this system,advance classification technique featuring Support Vector Machine and biologically inspired HMAX based shape descriptor integrated with biologically plausible RGB Opponent-Colour-Channel Descriptor is used to classify bakery products to their respective classes based on the shape and based on their colour referring to different baking durations. The results of this paper are compared with other methods for the automatic bakery products inspection. It is discovered that biologically inspired computer vision models performs accurately and efficiently as compared to the computer vision models which are not biologically plausible,in the bakery products quality inspection. It is also discovered that the One Versus One SVM and Directed Acyclic Graph SVM acquired the maximum accurate classification rate. The proposed method acquired classification accuracy of 95% and 100% for the biscuit shape and biscuit colour recognition,respectively. The proposed method is also consistently stable and invariant. This shows that the biologically inspired computer vision models have the capability to replace existing inspection methods as more reliable and accurate alternative.

Wang Jianming:Outdo Yourself or Outdo Your Opponent

IN his grade two at middle school, Wang Jianming took part in a study competition, and won first place in physics. The composition he wrote was chosen as a model essay. This first experience

N”世界新起点OPPON1绽放Coior时代

这世界如此流光溢彩 这世界如此五彩斑斓 这世界如此光怪陆离 这世界如此绚烂多姿

Adaptation of Ocular Opponency Neurons Mediates Attention-Induced Ocular Dominance Plasticity

Previous research has shown that ocular dominance can be biased by prolonged attention to one eye.The ocular-opponency-neuron model of binocular rivalry has been proposed as a candidate account for this phenomenon.Yet direct neural evidence is still lacking.By manipulating the contrast of dichoptic testing gratings,here we measured the steady-state visually evoked potentials(SSVEPs)at the intermodulation frequencies to selectively track the activities of ocular-opponency-neurons before and after the“dichoptic-backward-movie”adaptation.One hour of adaptation caused a shift of perceptual and neural ocular dominance towards the unattended eye.More importantly,we found a decrease in the intermodulation SSVEP response after adaptation,which was significantly greater when high-contrast gratings were presented to the attended eye than when they were presented to the unattended eye.These results strongly support the view that the adaptation of ocular-opponency-neurons contributes to the ocular dominance plasticity induced by prolonged eye-based attention.

Drogue detection for autonomous aerial refueling via hybrid pigeon-inspired optimized color opponent and saliency aggregation

Drogue detection is one of the challenging tasks in autonomous aerial refueling due to the requirement for accuracy and rapidity.Saliency detection based on image intrinsic cues can achieve fast detection,but with poor accuracy.Recent studies reveal that optimization-based methods provide accurate and quick solutions for saliency detection.This paper presents a hybrid pigeon-inspired optimization method,the optimized color opponent,that aims to adjust the weight of color opponent channels to detect the drogue region.It can optimize the weights in the selected aerial refueling scene offline,and the results are applied for drogue detection in the scene.A novel algorithm aggregated by the optimized color opponent and robust background detection is presented to provide better precision and robustness.Experimental results on benchmark datasets and aerial refueling images show that the proposed method successfully extracts the saliency region or drogue and exhibits superior performance against the other saliency detection methods with intrinsic cues.The algorithm designed in this paper is competent for the drogue detection task of autonomous aerial refueling.

Modulating a Local Shape Descriptor through Biologically Inspired Color Feature

This paper presents a biologically inspired local image descriptor that combines color and shape features. Compared with previous descriptors, red-cyan cells associated with L, M, and S cones （L for long, M for medium, and S for short） are used to indicate one of the opponent color channels. Stepping forward from state-of-the-art color feature extraction, we exploit a new approach to compute the color orientation and magnitudes of three opponent color channels, namely, red-green, blue-yellow, and red-cyan, in two-dimensional space. Color orientation is calculated in histograms with magnitude weighting. We linearly concatenate the four-color-opponent-channel histogram and scale-invariant-feamre-transform histogram in the final step. We apply our biologically inspired descriptor to describe the local image feature. Quantitative comparisons with state-of-the-art descriptors demonstrate the significant advantages of maintaining invariance to photometric and geometric changes in image matching, particularly in cases, such as illumination variation and image blurring, where more color contrast information is observed.