Matching Forensic Sketches to Mug Shot Photos Klare, Brendan; Zhifeng Li; Jain, A K
IEEE transactions on pattern analysis and machine intelligence,
03/2011, Letnik:
33, Številka:
3
Journal Article
Recenzirano
Odprti dostop
The problem of matching a forensic sketch to a gallery of mug shot images is addressed in this paper. Previous research in sketch matching only offered solutions to matching highly accurate sketches ...that were drawn while looking at the subject (viewed sketches). Forensic sketches differ from viewed sketches in that they are drawn by a police sketch artist using the description of the subject provided by an eyewitness. To identify forensic sketches, we present a framework called local feature-based discriminant analysis (LFDA). In LFDA, we individually represent both sketches and photos using SIFT feature descriptors and multiscale local binary patterns (MLBP). Multiple discriminant projections are then used on partitioned vectors of the feature-based representation for minimum distance matching. We apply this method to match a data set of 159 forensic sketches against a mug shot gallery containing 10,159 images. Compared to a leading commercial face recognition system, LFDA offers substantial improvements in matching forensic sketches to the corresponding face images. We were able to further improve the matching performance using race and gender information to reduce the target gallery size. Additional experiments demonstrate that the proposed framework leads to state-of-the-art accuracys when matching viewed sketches.
The problem of automatically matching composite sketches to facial photographs is addressed in this paper. Previous research on sketch recognition focused on matching sketches drawn by professional ...artists who either looked directly at the subjects (viewed sketches) or used a verbal description of the subject's appearance as provided by an eyewitness (forensic sketches). Unlike sketches hand drawn by artists, composite sketches are synthesized using one of the several facial composite software systems available to law enforcement agencies. We propose a component-based representation (CBR) approach to measure the similarity between a composite sketch and mugshot photograph. Specifically, we first automatically detect facial landmarks in composite sketches and face photos using an active shape model (ASM). Features are then extracted for each facial component using multiscale local binary patterns (MLBPs), and per component similarity is calculated. Finally, the similarity scores obtained from individual facial components are fused together, yielding a similarity score between a composite sketch and a face photo. Matching performance is further improved by filtering the large gallery of mugshot images using gender information. Experimental results on matching 123 composite sketches against two galleries with 10,123 and 1,316 mugshots show that the proposed method achieves promising performance (rank-100 accuracies of 77.2% and 89.4%, respectively) compared to a leading commercial face recognition system (rank-100 accuracies of 22.8% and 52.0%) and densely sampled MLBP on holistic faces (rank-100 accuracies of 27.6% and 10.6%). We believe our prototype system will be of great value to law enforcement agencies in apprehending suspects in a timely fashion.
This paper studies the influence of demographics on the performance of face recognition algorithms. The recognition accuracies of six different face recognition algorithms (three commercial, two ...nontrainable, and one trainable) are computed on a large scale gallery that is partitioned so that each partition consists entirely of specific demographic cohorts. Eight total cohorts are isolated based on gender (male and female), race/ethnicity (Black, White, and Hispanic), and age group (18-30, 30-50, and 50-70 years old). Experimental results demonstrate that both commercial and the nontrainable algorithms consistently have lower matching accuracies on the same cohorts (females, Blacks, and age group 18-30) than the remaining cohorts within their demographic. Additional experiments investigate the impact of the demographic distribution in the training set on the performance of a trainable face recognition algorithm. We show that the matching accuracy for race/ethnicity and age cohorts can be improved by training exclusively on that specific cohort. Operationally, this leads to a scenario, called dynamic face matcher selection, where multiple face recognition algorithms (each trained on different demographic cohorts) are available for a biometric system operator to select based on the demographic information extracted from a probe image. This procedure should lead to improved face recognition accuracy in many intelligence and law enforcement face recognition scenarios. Finally, we show that an alternative to dynamic face matcher selection is to train face recognition algorithms on datasets that are evenly distributed across demographics, as this approach offers consistently high accuracy across all cohorts.
This paper presents a framework for component-based face alignment and representation that demonstrates improvements in matching performance over the more common holistic approach to face alignment ...and representation. This work is motivated by recent evidence from the cognitive science community demonstrating the efficacy of component-based facial representations. The component-based framework presented in this paper consists of the following major steps: 1) landmark extraction using Active Shape Models (ASM), 2) alignment and cropping of components using Procrustes Analysis, 3) representation of components with Multiscale Local Binary Patterns (MLBP), 4) per-component measurement of facial similarity, and 5) fusion of per-component similarities. We demonstrate on three public datasets and an operational dataset consisting of face images of 8000 subjects, that the proposed component-based representation provides higher recognition accuracies over holistic-based representations. Additionally, we show that the proposed component-based representations: 1) are more robust to changes in facial pose, and 2) improve recognition accuracy on occluded face images in forensic scenarios.
The combination of carboplatin and topotecan in platinum-sensitive relapsed ovarian cancer could not improve progression-free survival or overall survival compared with established standard regimens.
...Randomized, phase III trial to evaluate safety and efficacy of topotecan and carboplatin (TC) compared with standard platinum-based combinations in platinum-sensitive recurrent ovarian cancer (ROC).
Patients were randomly assigned in a 1:1 ratio to the experimental TC arm (topotecan 0.75 mg/m2/ days 1–3 and carboplatin AUC 5 on day 3 every 3 weeks) or to one of the standard regimes (PC) paclitaxel plus carboplatin; (GC) gemcitabine plus carboplatin; (PLDC) pegylated liposomal doxorubicin and carboplatin which could be chosen by individual preference but before randomization. The primary end point was progression-free survival (PFS) after 12 months. Overall survival (OS), response rate, toxicity, quality of life and treatment preference regarding standard treatment were defined as secondary end points.
A total of 550 patients were recruited. The PFS rate after 12 months was 37.0% for TC compared with 40.2% in the standard combinations (P = 0.470). The overall response rate was 73.1% for TC versus 75.1% for standard combinations (P = 0.149). After a median follow-up of 20 months, the median PFS was 10 months 95% confidence interval (CI) 9.4–10.6 and did not differ between both arms (P = 0.414). The median OS was 25 months in the TC arm versus 31 months in the standard arm (95% CI: 22.4–27.6 resp. 26.0–36.0; P = 0.163). Severe hematologic toxicities (grade 3/4) were rare in the experimental arm (P < 0.001), with 17.4% leucopenia, 27.8% neutropenia and 15.9% thrombopenia.
The combination of carboplatin and topotecan was well tolerated with significant lower rates of severe hematological toxicities but did not improve PFS or OS in platinum-sensitive relapsed ovarian cancer compared with established standard regimens.
Matching near-infrared (NIR) face images to visible light (VIS) face images offers a robust approach to face recognition with unconstrained illumination. In this paper we propose a novel method of ...heterogeneous face recognition that uses a common feature-based representation for both NIR images as well as VIS images. Linear discriminant analysis is performed on a collection of random subspaces to learn discriminative projections. NIR and VIS images are matched (i) directly using the random subspace projections, and (ii) using sparse representation classification. Experimental results demonstrate the effectiveness of the proposed approach for matching NIR and VIS face images.
This study details a modular and general synthesis of a new class of molecules consisting of cruciform π-systems. The key to synthesizing these molecules was an unprecedented double Staudinger ...cyclization. Once formed, these rigid compounds assemble into ordered monolayer films on metal and metal oxide surfaces to orient their conjugated, bis-phenyloxazole subunits upright. This surface orientation is enforced by the external phenyl substituents that are out of the ring plane, thus preventing the prone conformation.
We recently reported a new method for the direct dehydrogenative C–H silylation of heteroaromatics utilizing Earth-abundant potassium tert-butoxide. Herein we report a systematic experimental and ...computational mechanistic investigation of this transformation. Our experimental results are consistent with a radical chain mechanism. A trialkylsilyl radical may be initially generated by homolytic cleavage of a weakened Si–H bond of a hypercoordinated silicon species as detected by IR, or by traces of oxygen which can generate a reactive peroxide by reaction with KOt-Bu4 as indicated by density functional theory (DFT) calculations. Radical clock and kinetic isotope experiments support a mechanism in which the C–Si bond is formed through silyl radical addition to the heterocycle followed by subsequent β-hydrogen scission. DFT calculations reveal a reasonable energy profile for a radical mechanism and support the experimentally observed regioselectivity. The silylation reaction is shown to be reversible, with an equilibrium favoring products due to the generation of H2 gas. In situ NMR experiments with deuterated substrates show that H2 is formed by a cross-dehydrogenative mechanism. The stereochemical course at the silicon center was investigated utilizing a 2H-labeled silolane probe; complete scrambling at the silicon center was observed, consistent with a number of possible radical intermediates or hypercoordinate silicates.
Heterogeneous face recognition (HFR) involves matching two face images from alternate imaging modalities, such as an infrared image to a photograph or a sketch to a photograph. Accurate HFR systems ...are of great value in various applications (e.g., forensics and surveillance), where the gallery databases are populated with photographs (e.g., mug shot or passport photographs) but the probe images are often limited to some alternate modality. A generic HFR framework is proposed in which both probe and gallery images are represented in terms of nonlinear similarities to a collection of prototype face images. The prototype subjects (i.e., the training set) have an image in each modality (probe and gallery), and the similarity of an image is measured against the prototype images from the corresponding modality. The accuracy of this nonlinear prototype representation is improved by projecting the features into a linear discriminant subspace. Random sampling is introduced into the HFR framework to better handle challenges arising from the small sample size problem. The merits of the proposed approach, called prototype random subspace (P-RS), are demonstrated on four different heterogeneous scenarios: 1) near infrared (NIR) to photograph, 2) thermal to photograph, 3) viewed sketch to photograph, and 4) forensic sketch to photograph.